© 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. 11812
    Prev
    Next
    INDEX
    Explanations

    references to political and societal issues related to government policies, social classes, and criticism

    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
    160
    +0.23
    0.8%
    276
    +0.15
    0.5%
    314
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.23
    0.06
    276
    +0.15
    0.05
    78
    +0.14
    0.05
    Negative Logits
     mathemat
    -1.12
     Seym
    -1.10
     condem
    -1.03
     disadvant
    -1.01
     explan
    -1.01
     welf
    -1.00
     pestic
    -0.98
     metic
    -0.98
     seiz
    -0.98
     Citiz
    -0.95
    POSITIVE LOGITS
    ï¸ı
    1.48
    lean
    1.42
    vernment
    1.26
    log
    1.20
    leans
    1.13
    âĹ¼
    1.11
    £
    1.11
    resent
    1.09
    PT
    1.07
    MQ
    1.07
    Activations Density 0.258%

    No Known Activations