© 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. 34734
    Prev
    Next
    INDEX
    Explanations

    cooperation-related terms or phrases

    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
    +0.25
    1.2%
    151
    +0.12
    0.6%
    665
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.25
    0.18
    195
    +0.12
    0.03
    151
    +0.12
    0.20
    Negative Logits
    ãĥª
    -0.74
    arth
    -0.68
    nic
    -0.66
    mental
    -0.66
    fing
    -0.65
    brid
    -0.65
    bred
    -0.64
    marked
    -0.64
    season
    -0.59
    tha
    -0.58
    POSITIVE LOGITS
     favorably
    0.93
     extensively
    0.92
     positively
    0.89
     withd
    0.88
     peacefully
    0.88
     forcefully
    0.86
     negatively
    0.81
     violently
    0.81
     aggressively
    0.81
     vigorously
    0.80
    Activations Density 11.368%

    No Known Activations