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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 4107
    Prev
    Next
    INDEX
    Explanations

    flamboyant and vibrant descriptions or names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.17
    0.6%
    428
    +0.14
    0.5%
    144
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.17
    0.12
    43
    +0.14
    0.09
    640
    +0.13
    0.23
    Negative Logits
    CHR
    -1.05
    éŃĶ
    -0.87
    DEBUG
    -0.87
    200000
    -0.85
    BIL
    -0.81
    CLASSIFIED
    -0.79
    Lago
    -0.79
    soType
    -0.79
     Kard
    -0.78
    ãĥ¯ãĥ³
    -0.78
    POSITIVE LOGITS
    uating
    1.11
    idation
    1.09
    idated
    1.06
    owship
    1.06
    ruary
    1.01
    odor
    0.99
    ishing
    0.99
    agles
    0.94
    erer
    0.92
    arty
    0.91
    Activations Density 12.163%

    No Known Activations