© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 2579
    Prev
    Next
    INDEX
    Explanations

    phrases related to recounting experiences or hearing about situations

    oai_token-act-pair · gpt-3.5-turbo

    instances where the word "about" is used to introduce a topic or subject matter

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    270
    +0.16
    0.7%
    393
    +0.15
    0.7%
    311
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.16
    0.05
    155
    +0.15
    0.05
    723
    +0.12
    0.04
    Negative Logits
     teasp
    -0.86
    hesis
    -0.74
    emo
    -0.73
    hat
    -0.72
     Held
    -0.72
    hai
    -0.71
    held
    -0.71
    ©¶æ¥µ
    -0.71
    waters
    -0.70
    rang
    -0.68
    POSITIVE LOGITS
     calib
    0.77
    PsyNetMessage
    0.71
     how
    0.70
     them
    0.70
    dust
    0.69
     tomorrow
    0.69
    addons
    0.67
     EVE
    0.66
     improving
    0.66
     these
    0.64
    Activations Density 0.620%

    No Known Activations