© 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. 36849
    Prev
    Next
    INDEX
    Explanations

    information related to environmental issues and politics

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    197
    +0.09
    0.4%
    356
    +0.09
    0.4%
    316
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.09
    0.10
    316
    +0.09
    0.13
    6
    +0.09
    0.18
    Negative Logits
    fman
    -0.85
    igmatic
    -0.65
    gart
    -0.65
    worms
    -0.65
     bleach
    -0.65
    utra
    -0.65
     toast
    -0.64
    helps
    -0.63
     cheeks
    -0.61
     rever
    -0.61
    POSITIVE LOGITS
     Establishment
    0.87
     Regulatory
    0.84
     Directorate
    0.76
     Bureau
    0.74
    Administ
    0.70
    Journal
    0.69
     Intelligence
    0.69
     Journalism
    0.69
    :{
    0.69
     Appropriations
    0.68
    Activations Density 16.597%

    No Known Activations