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

    Neuronpedia

    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. 5805
    Prev
    Next
    INDEX
    Explanations

    links to academic papers

    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
    208
    +0.09
    0.5%
    114
    +0.08
    0.4%
    7
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.09
    0.01
    4
    +0.08
    0.01
    231
    +0.07
    0.01
    Negative Logits
    é¾įå
    -0.61
    unia
    -0.59
    stock
    -0.59
    eless
    -0.59
    ãĥĪ
    -0.58
     gel
    -0.57
    comb
    -0.57
     negatively
    -0.56
    DW
    -0.55
     Ivanka
    -0.55
    POSITIVE LOGITS
    ailable
    0.70
    ittal
    0.69
    ibrary
    0.63
    bidden
    0.62
    eming
    0.62
     Telegram
    0.59
     proofs
    0.59
    umbers
    0.59
     Transactions
    0.58
     theorem
    0.57
    Activations Density 0.010%

    No Known Activations