© 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. 45991
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific groups related to politics and cinema

    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
    578
    +0.12
    0.7%
    746
    +0.08
    0.5%
    302
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.27
    326
    +0.08
    0.27
    575
    +0.08
    0.16
    Negative Logits
     Lif
    -0.59
    LOAD
    -0.59
    itud
    -0.56
    down
    -0.55
    downs
    -0.55
    ð
    -0.55
    ithub
    -0.54
    inals
    -0.52
    ľ
    -0.52
    heart
    -0.51
    POSITIVE LOGITS
    ervative
    1.00
    ervatives
    0.78
    ROR
    0.51
     intellectuals
    0.48
    ilogy
    0.48
    emporary
    0.48
    SpaceEngineers
    0.47
    schild
    0.47
    omsky
    0.47
    prototype
    0.46
    Activations Density 12.018%

    No Known Activations