© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13708
    Prev
    Next
    INDEX
    Explanations

    phrases indicating involvement in the entertainment industry

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    393
    +0.20
    0.9%
    385
    +0.11
    0.5%
    339
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.20
    0.15
    22
    +0.11
    0.14
    608
    +0.10
    0.17
    Negative Logits
    rama
    -0.82
    mb
    -0.73
     convol
    -0.70
     inexper
    -0.66
    llor
    -0.65
    ynes
    -0.65
     learners
    -0.64
     clocks
    -0.63
     mathemat
    -0.62
    ν
    -0.62
    POSITIVE LOGITS
     upcoming
    0.75
    ordinate
    0.74
    ducers
    0.73
    etime
    0.73
    thood
    0.72
    versions
    0.71
     various
    0.71
     prestigious
    0.69
     numerous
    0.68
     Standing
    0.68
    Activations Density 4.572%

    No Known Activations