Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13870
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals named Louis

    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
    68
    +0.16
    0.5%
    553
    +0.16
    0.5%
    679
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.08
    326
    +0.16
    0.06
    346
    +0.15
    0.05
    Negative Logits
    cffffcc
    -1.19
    ference
    -1.10
    TPP
    -1.08
    BOOK
    -1.07
    bably
    -1.03
    fig
    -0.96
    VALUE
    -0.96
    ptive
    -0.94
    ãĤ©
    -0.94
    BALL
    -0.94
    POSITIVE LOGITS
     CK
    1.45
     XIV
    1.22
     XVI
    1.16
    ouri
    1.11
     Rams
    1.07
     Vu
    1.06
     Blues
    1.06
     Angeles
    1.06
     Armstrong
    1.02
    esian
    1.02
    Activations Density 0.778%

    No Known Activations