© 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. 1536
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    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
    +0.13
    0.5%
    288
    +0.13
    0.5%
    377
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    57
    +0.13
    0.03
    288
    +0.13
    0.05
    659
    +0.12
    0.03
    Negative Logits
     Dayton
    -0.85
    WARE
    -0.82
    swick
    -0.81
     Proposition
    -0.81
    eering
    -0.79
    eers
    -0.79
     Tacoma
    -0.78
    DOWN
    -0.78
    creen
    -0.78
    nings
    -0.76
    POSITIVE LOGITS
    ilst
    1.03
    ouls
    1.02
    oses
    0.97
    ilit
    0.93
    azi
    0.93
    oul
    0.89
    ils
    0.87
    RH
    0.86
    acha
    0.86
    iled
    0.86
    Activations Density 0.432%

    No Known Activations