© 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. 45937
    Prev
    Next
    INDEX
    Explanations

    questions starting with "How" and "Does."

    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
    0.7%
    483
    +0.12
    0.5%
    88
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.17
    0.24
    640
    +0.12
    0.22
    275
    +0.12
    0.05
    Negative Logits
    HB
    -0.81
     Skydragon
    -0.80
    hao
    -0.74
    xxxxxxxx
    -0.74
    cca
    -0.70
    ru
    -0.70
    BS
    -0.69
    vic
    -0.69
    ãĥĩãĤ£
    -0.69
    ca
    -0.67
    POSITIVE LOGITS
    ?]
    0.76
     heck
    0.73
     reconcil
    0.69
     regenerate
    0.66
    ?),
    0.66
     hell
    0.66
     Lanka
    0.66
    riad
    0.65
     reconcile
    0.65
     coping
    0.64
    Activations Density 10.281%

    No Known Activations