© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14187
    Prev
    Next
    INDEX
    Explanations

    interrogative questions and statements that express skepticism or disbelief, particularly regarding social and political issues

    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
    +0.29
    1.2%
    393
    +0.11
    0.5%
    125
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    561
    +0.29
    0.13
    393
    +0.11
    0.26
    142
    +0.10
    0.11
    Negative Logits
    ãģ®ç
    -0.80
    "],
    -0.78
    ipeg
    -0.78
    bies
    -0.75
    rolet
    -0.75
    mares
    -0.74
    Fill
    -0.74
    CTV
    -0.73
    hester
    -0.72
    ioch
    -0.70
    POSITIVE LOGITS
     kidding
    0.84
     worth
    0.81
     really
    0.80
     truly
    0.78
     gonna
    0.77
     intentional
    0.76
     complicit
    0.76
     supposed
    0.76
     indicative
    0.76
     acceptable
    0.76
    Activations Density 11.557%

    No Known Activations