© 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
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 4176
    Prev
    Next
    INDEX
    Explanations

    verbs related to concrete actions or knowledge acquisition

    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
    213
    +0.10
    0.6%
    694
    +0.10
    0.6%
    679
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.10
    479
    +0.10
    0.03
    282
    +0.08
    0.08
    Negative Logits
    boa
    -0.68
    otion
    -0.63
    ŃĶ
    -0.62
    otos
    -0.62
    erva
    -0.61
    aminer
    -0.60
    enda
    -0.59
    rid
    -0.58
    ÅĤ
    -0.58
     Dj
    -0.57
    POSITIVE LOGITS
    lege
    0.57
    cut
    0.54
     beforehand
    0.54
    ledged
    0.53
     Aware
    0.52
    ãĥĨ
    0.51
     Benefit
    0.51
    itarian
    0.50
    stood
    0.49
     hardship
    0.48
    Activations Density 5.967%

    No Known Activations