© 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. 12241
    Prev
    Next
    INDEX
    Explanations

    specific phrases that indicate giving or providing information or context

    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%
    34
    +0.12
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.20
    0.13
    393
    +0.12
    0.14
    362
    +0.11
    0.08
    Negative Logits
    GES
    -0.78
    untary
    -0.72
    Hum
    -0.71
    Reviewed
    -0.70
    iate
    -0.68
    renheit
    -0.67
    vous
    -0.67
    dn
    -0.66
    eva
    -0.66
    ür
    -0.66
    POSITIVE LOGITS
     circumstances
    1.20
     circumstance
    1.00
     sheer
    0.99
     uncertainties
    0.96
     pressures
    0.95
     constraints
    0.94
     lack
    0.92
     absence
    0.90
     ramifications
    0.88
     inexper
    0.87
    Activations Density 2.516%

    No Known Activations