© 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 EvalsExportsAPI 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. 189
    Prev
    Next
    INDEX
    Explanations

    questions and uncertainties expressed in a narrative or dialogue format

    oai_token-act-pair · gpt-3.5-turbo
    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
    523
    +0.13
    0.6%
    398
    +0.11
    0.5%
    584
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.13
    0.07
    584
    +0.11
    0.07
    360
    +0.10
    0.07
    Negative Logits
    tein
    -0.81
     Jinn
    -0.73
     Nightmare
    -0.66
     vain
    -0.65
     Bom
    -0.64
    mania
    -0.62
     Niet
    -0.60
    espie
    -0.60
     Compan
    -0.59
     composing
    -0.59
    POSITIVE LOGITS
    everal
    0.80
    aternity
    0.70
    endale
    0.69
    abouts
    0.69
    ileged
    0.69
    othal
    0.68
     occasions
    0.68
    vice
    0.68
    uable
    0.67
    omen
    0.67
    Activations Density 0.923%

    No Known Activations