© 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 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. 371
    Prev
    Next
    INDEX
    Explanations

    phrases expressing approval, validation, or agreement

    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
    151
    +0.13
    0.5%
    140
    +0.12
    0.5%
    52
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.12
    99
    +0.12
    0.06
    103
    +0.12
    0.06
    Negative Logits
    orem
    -0.87
     Activities
    -0.83
    igraph
    -0.82
    oleon
    -0.82
    iments
    -0.79
     Delivery
    -0.77
     Enhancement
    -0.77
     Killer
    -0.77
     Occupations
    -0.76
    ospace
    -0.76
    POSITIVE LOGITS
    ãĤ©
    1.23
    olded
    0.93
    named
    0.92
    mint
    0.87
     accommod
    0.84
    gged
    0.84
     positioned
    0.84
     bestowed
    0.83
    label
    0.82
     fitted
    0.82
    Activations Density 1.324%

    No Known Activations