© 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. 8342
    Prev
    Next
    INDEX
    Explanations

    references to staying or running in a particular location or state

    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
    652
    +0.14
    0.5%
    98
    +0.14
    0.5%
    603
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.14
    0.08
    126
    +0.14
    0.06
    665
    +0.14
    0.10
    Negative Logits
    senal
    -0.81
    Els
    -0.78
    terness
    -0.75
     welcome
    -0.74
    eteenth
    -0.73
     awaiting
    -0.73
    \\\\\\\\
    -0.72
    ©¶æ¥µ
    -0.72
    ighth
    -0.69
    scape
    -0.68
    POSITIVE LOGITS
    eret
    0.83
    essor
    0.80
     <=
    0.78
     correctly
    0.74
     >=
    0.73
     sufficiently
    0.73
    starter
    0.71
    ume
    0.70
    zero
    0.69
     hindsight
    0.68
    Activations Density 3.566%

    No Known Activations