© 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. 32839
    Prev
    Next
    INDEX
    Explanations

    names, positions, and activities related to political figures and sports teams

    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
    398
    +0.13
    0.5%
    579
    +0.13
    0.4%
    432
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.13
    0.01
    398
    +0.13
    0.08
    232
    +0.12
    0.08
    Negative Logits
    furt
    -0.95
    Daily
    -0.88
     reluct
    -0.87
    oway
    -0.87
     rall
    -0.84
    ernaut
    -0.83
     tremend
    -0.79
     Klux
    -0.78
     acknow
    -0.78
    CHO
    -0.77
    POSITIVE LOGITS
    ttes
    1.15
     Jub
    0.91
    mony
    0.88
    vironments
    0.87
    vironment
    0.86
     Cou
    0.86
    ionage
    0.85
     Throne
    0.85
     Comet
    0.84
    hern
    0.84
    Activations Density 14.553%

    No Known Activations