© 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. 962
    Prev
    Next
    INDEX
    Explanations

    names of a specific individual - Ron Paul - who seems to be involved in various contexts and topics

    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
    421
    +0.20
    0.6%
    376
    +0.17
    0.6%
    497
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.20
    0.06
    288
    +0.17
    0.09
    343
    +0.17
    0.06
    Negative Logits
     sugg
    -0.92
    hower
    -0.92
     Chiefs
    -0.91
     Dakota
    -0.89
     Pixie
    -0.89
     td
    -0.88
    displayText
    -0.84
    ORD
    -0.84
     prelim
    -0.84
     rigging
    -0.83
    POSITIVE LOGITS
    ald
    1.48
    aldo
    1.43
     Weasley
    1.37
    nie
    1.33
    ny
    1.33
     Swanson
    1.26
    igans
    1.20
    stadt
    1.19
    liest
    1.19
    ners
    1.17
    Activations Density 1.196%

    No Known Activations