© 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. 13561
    Prev
    Next
    INDEX
    Explanations

    references to organizations, programs, and institutions

    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
    288
    +0.17
    0.6%
    457
    +0.13
    0.5%
    644
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.17
    0.17
    288
    +0.13
    0.17
    455
    +0.13
    0.14
    Negative Logits
    poons
    -0.97
    azeera
    -0.96
    sbm
    -0.93
    NetMessage
    -0.90
     Lanka
    -0.89
    %%%%
    -0.85
    poon
    -0.85
    htaking
    -0.82
    gements
    -0.82
    borgh
    -0.81
    POSITIVE LOGITS
     itself
    1.46
    's
    1.25
    osphere
    1.11
    wide
    1.09
    ultimate
    1.03
     motto
    0.95
    runners
    0.94
     administrator
    0.92
     formerly
    0.87
     abruptly
    0.87
    Activations Density 2.728%

    No Known Activations