© 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 EvalsExportsinterp-engineNEWAPI 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. 11641
    Prev
    Next
    INDEX
    Explanations

    names and titles of people, particularly those related to legal and political contexts

    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
    326
    +0.13
    0.7%
    185
    +0.10
    0.5%
    417
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.13
    0.01
    107
    +0.10
    0.04
    103
    +0.09
    0.06
    Negative Logits
     redes
    -0.91
    ãĢİ
    -0.76
     conclud
    -0.73
    ä¿
    -0.71
     horizont
    -0.70
     fundament
    -0.69
     lawy
    -0.69
     conflic
    -0.68
     explan
    -0.67
     derog
    -0.66
    POSITIVE LOGITS
    âĢ¢âĢ¢
    0.85
    tf
    0.72
    ICE
    0.66
    iri
    0.65
    hunter
    0.65
    -.
    0.65
    cks
    0.63
    fi
    0.62
    nir
    0.62
    NO
    0.62
    Activations Density 0.598%

    No Known Activations