© 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. 33043
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by verbs in infinitive form

    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
    +0.16
    0.7%
    672
    +0.10
    0.5%
    665
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.16
    0.27
    447
    +0.10
    0.30
    64
    +0.10
    -0.25
    Negative Logits
     irony
    -0.78
     understatement
    -0.70
     downside
    -0.65
     pse
    -0.63
     contraction
    -0.63
     cautioned
    -0.61
     setback
    -0.61
    wikipedia
    -0.60
     Mayer
    -0.59
     lately
    -0.59
    POSITIVE LOGITS
    sylv
    0.84
     safely
    0.75
    ilater
    0.74
    anqu
    0.72
     satisfy
    0.71
    shed
    0.68
    agy
    0.67
     continue
    0.66
     maximize
    0.65
    ctic
    0.65
    Activations Density 14.244%

    No Known Activations