© 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. 11247
    Prev
    Next
    INDEX
    Explanations

    statements or quotes beginning with or related to the word "say."

    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
    195
    +0.13
    0.5%
    274
    +0.11
    0.4%
    236
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.13
    0.08
    195
    +0.11
    0.03
    274
    +0.11
    0.06
    Negative Logits
     hemor
    -0.85
     Bullets
    -0.82
     flo
    -0.82
    rawdownloadcloneembedreportprint
    -0.81
    ãĤ´ãĥ³
    -0.80
     datas
    -0.78
     captcha
    -0.77
    pes
    -0.75
     srf
    -0.73
     Seym
    -0.73
    POSITIVE LOGITS
    enance
    1.28
    ensional
    0.96
    doi
    0.91
    brush
    0.91
    abl
    0.87
    ign
    0.86
    ellect
    0.84
     definitively
    0.82
    rack
    0.82
    agne
    0.81
    Activations Density 0.978%

    No Known Activations