© 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. 37090
    Prev
    Next
    INDEX
    Explanations

    legal and political terms in news articles

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms followed by a period

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @jordan
    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
    356
    +0.07
    0.5%
    116
    +0.07
    0.5%
    68
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.07
    0.16
    6
    +0.07
    0.20
    314
    +0.07
    -0.04
    Negative Logits
    »Ĵ
    -0.71
    =-=-
    -0.50
    ÙIJ
    -0.48
    Ħ¢
    -0.47
    Ö¼
    -0.47
    achi
    -0.46
    merce
    -0.46
    -->
    -0.43
    perty
    -0.43
    -+-+
    -0.43
    POSITIVE LOGITS
    ateral
    0.69
    ounge
    0.58
    aptop
    0.54
    uce
    0.54
    oreal
    0.51
    ocating
    0.51
    omez
    0.51
    ushing
    0.50
    ouver
    0.50
    igne
    0.50
    Activations Density 12.008%

    No Known Activations