© 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. 31461
    Prev
    Next
    INDEX
    Explanations

    references related to legal cases and political figures, particularly focusing on charges and testimony

    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
    447
    +0.09
    1.0%
    288
    +0.08
    0.9%
    662
    +0.05
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.09
    0.05
    15
    +0.08
    0.11
    86
    +0.05
    0.05
    Negative Logits
    ĸļ
    -0.40
    Redd
    -0.36
    enance
    -0.33
    µ
    -0.30
     Marathon
    -0.30
    Sund
    -0.30
    IJ
    -0.30
    Rated
    -0.29
    Haw
    -0.28
    ľ
    -0.28
    POSITIVE LOGITS
    uchin
    0.42
    umenthal
    0.40
    afort
    0.37
    wagen
    0.35
    anyahu
    0.33
    hattan
    0.32
    agements
    0.31
    tsky
    0.30
    ises
    0.30
    anches
    0.29
    Activations Density 8.833%

    No Known Activations