© 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. 13129
    Prev
    Next
    INDEX
    Explanations

    mentions of historical places and 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
    583
    +0.14
    0.7%
    649
    +0.11
    0.5%
    77
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.14
    0.45
    6
    +0.11
    0.27
    64
    +0.10
    -0.23
    Negative Logits
    »Ĵ
    -0.64
    amins
    -0.63
    perty
    -0.63
    anova
    -0.62
     snag
    -0.61
    atu
    -0.61
    aintain
    -0.60
    achu
    -0.60
     issuer
    -0.60
    =-=-=-=-
    -0.59
    POSITIVE LOGITS
     coli
    0.98
     Cul
    0.70
     Moss
    0.67
     fashioned
    0.63
     Coy
    0.62
    gypt
    0.62
    911
    0.61
     Pas
    0.61
     Marie
    0.61
     Sed
    0.60
    Activations Density 11.135%

    No Known Activations