© 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. 7611
    Prev
    Next
    INDEX
    Explanations

    references to autographs and the act of signing them

    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
    569
    +0.21
    0.8%
    288
    +0.18
    0.7%
    640
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.21
    0.15
    232
    +0.18
    0.09
    0
    +0.15
    0.09
    Negative Logits
    FORE
    -0.99
    FUL
    -0.94
    UTION
    -0.91
    lihood
    -0.89
     Fargo
    -0.86
    LY
    -0.86
    BuyableInstoreAndOnline
    -0.86
    lda
    -0.85
     Bir
    -0.85
    xual
    -0.85
    POSITIVE LOGITS
    ographs
    1.99
    ograph
    1.77
    ographed
    1.61
    ographic
    1.51
    odynam
    1.47
    ogyn
    1.45
    ograp
    1.39
    opl
    1.39
    icles
    1.39
    ocon
    1.38
    Activations Density 2.408%

    No Known Activations