© 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. 8675
    Prev
    Next
    INDEX
    Explanations

    references to governmental policies and actions, particularly related to security and international relations

    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
    581
    +0.20
    0.7%
    393
    +0.19
    0.6%
    159
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.20
    0.03
    581
    +0.19
    0.03
    333
    +0.13
    0.03
    Negative Logits
    bling
    -1.08
     Duchess
    -1.03
    politics
    -1.02
    fo
    -1.02
    nin
    -1.00
    arter
    -0.99
    ben
    -0.99
    tty
    -0.96
    bug
    -0.96
    viks
    -0.96
    POSITIVE LOGITS
     dearly
    1.23
    soever
    1.11
    amac
    0.99
    velength
    0.96
    emetery
    0.90
     transfers
    0.90
     appraisal
    0.86
     newsletters
    0.85
    xual
    0.84
     hereafter
    0.84
    Activations Density 0.188%

    No Known Activations