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

    Neuronpedia

    Jacobian LensNEW
    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. 33190
    Prev
    Next
    INDEX
    Explanations

    information related to social or political relevance, including legal concepts, societal issues, and historical events

    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
    +0.14
    0.7%
    393
    +0.13
    0.7%
    396
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.19
    284
    +0.13
    0.09
    643
    +0.12
    0.04
    Negative Logits
    imity
    -0.74
    EMENT
    -0.72
    autions
    -0.67
    antage
    -0.66
    uto
    -0.65
    bilt
    -0.64
    FTWARE
    -0.63
    ISSION
    -0.61
     largeDownload
    -0.60
    umbn
    -0.60
    POSITIVE LOGITS
     usual
    0.86
     ever
    0.74
     anything
    0.69
     placebo
    0.67
     others
    0.65
    acles
    0.64
     superficial
    0.61
     ours
    0.60
     bother
    0.58
     anybody
    0.58
    Activations Density 6.276%

    No Known Activations