© 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. 6146
    Prev
    Next
    INDEX
    Explanations

    numbers indicating large quantities

    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
    288
    +0.17
    0.6%
    657
    +0.14
    0.5%
    610
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    657
    +0.17
    0.07
    132
    +0.14
    0.05
    698
    +0.13
    0.05
    Negative Logits
    imen
    -1.08
    mentioned
    -0.92
    aign
    -0.92
    ivalry
    -0.92
     Armory
    -0.91
     Correspond
    -0.91
    iban
    -0.91
    imir
    -0.90
    NER
    -0.88
    ãĥ¤
    -0.88
    POSITIVE LOGITS
     dollars
    1.22
    aires
    1.20
     ILCS
    1.16
     lashes
    1.08
    aire
    1.05
     bucks
    1.03
     pounds
    0.99
    bucks
    0.97
     euros
    0.97
     gallons
    0.97
    Activations Density 1.095%

    No Known Activations