© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate causation or influence

    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
    +0.22
    1.4%
    393
    +0.11
    0.7%
    665
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.22
    0.21
    665
    +0.11
    0.18
    718
    +0.10
    0.18
    Negative Logits
    anooga
    -0.59
     fortun
    -0.53
     lett
    -0.44
    oret
    -0.41
    resy
    -0.41
    jon
    -0.41
    FX
    -0.41
     Prediction
    -0.41
     fucked
    -0.40
     Legions
    -0.40
    POSITIVE LOGITS
     stumble
    0.70
     pursue
    0.67
     realize
    0.64
     ponder
    0.62
    ãĤ©
    0.60
     rethink
    0.60
     contemplate
    0.60
     reconsider
    0.60
    othy
    0.60
     conclude
    0.60
    Activations Density 9.699%

    No Known Activations