© 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. 37167
    Prev
    Next
    INDEX
    Explanations

    words related to government, politics, and international affairs

    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
    447
    +0.21
    0.9%
    57
    +0.15
    0.6%
    311
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.21
    0.11
    57
    +0.15
    0.08
    643
    +0.15
    0.05
    Negative Logits
    tics
    -0.82
    mercial
    -0.82
    lessly
    -0.81
    papers
    -0.81
    theless
    -0.77
    breaks
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.73
     Turing
    -0.72
    ships
    -0.71
    ancial
    -0.71
    POSITIVE LOGITS
    igon
    1.14
    adish
    1.12
    iva
    1.09
    pling
    1.08
    plings
    1.06
    eed
    1.03
    uth
    1.03
    uten
    1.02
    Ga
    1.02
    vers
    1.01
    Activations Density 6.246%

    No Known Activations