© 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. 36973
    Prev
    Next
    INDEX
    Explanations

    specific legislative bill numbers

    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
    +0.19
    0.9%
    620
    +0.12
    0.6%
    719
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.19
    -0.03
    127
    +0.12
    0.08
    6
    +0.10
    0.14
    Negative Logits
    panic
    -0.70
    inations
    -0.66
    opian
    -0.65
    etimes
    -0.62
    querque
    -0.60
    TPPStreamerBot
    -0.59
    eals
    -0.58
     mute
    -0.58
     relegation
    -0.57
     addicted
    -0.57
    POSITIVE LOGITS
    XXX
    0.87
    CV
    0.86
    cv
    0.85
    DH
    0.85
    DEN
    0.81
    ZE
    0.81
    01
    0.81
    DM
    0.81
    651
    0.80
    eus
    0.80
    Activations Density 10.921%

    No Known Activations