© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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 Local
    9. 6-RES_SCL-AJT
    11. 37221
    Prev
    Next
    INDEX
    Explanations

    content related to political figures and economic strategies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    Neuron Alignment
    Index
    Value
    % of L₁
    564
    +0.13
    0.6%
    632
    +0.11
    0.5%
    194
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    731
    +0.13
    0.03
    62
    +0.11
    0.04
    306
    +0.10
    0.07
    Negative Logits
    quartered
    -0.83
    essee
    -0.77
    rehens
    -0.75
    ourgeois
    -0.75
     Morg
    -0.73
    ISON
    -0.72
    naire
    -0.70
    laus
    -0.70
    ansas
    -0.70
    ional
    -0.69
    POSITIVE LOGITS
     roundup
    0.82
     newsletter
    0.80
     dose
    0.77
     updates
    0.77
     subscription
    0.73
     reminder
    0.73
     notification
    0.71
     certs
    0.70
     weekday
    0.70
     newsletters
    0.69
    Activations Density 5.884%

    No Known Activations