© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6827
    Prev
    Next
    INDEX
    Explanations

    references or mentions of legal or political disputes and conflicts

    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
    +0.33
    1.3%
    679
    +0.25
    1.0%
    274
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.33
    0.10
    69
    +0.25
    0.08
    512
    +0.15
    0.07
    Negative Logits
    tails
    -0.81
    oses
    -0.80
    ress
    -0.79
    ãĥĺ
    -0.76
    ãĥ¬
    -0.76
    Pont
    -0.75
    backer
    -0.74
    ETS
    -0.73
    izont
    -0.71
    estern
    -0.71
    POSITIVE LOGITS
     although
    1.04
     "[
    0.93
     sounded
    0.90
    soever
    0.86
     they
    0.83
     accompanies
    0.82
     "#
    0.80
     '[
    0.75
     contrasts
    0.75
     evening
    0.74
    Activations Density 0.843%

    No Known Activations