© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8773
    Prev
    Next
    INDEX
    Explanations

    pieces of information related to legal or criminal issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    434
    +0.05
    0.5%
    256
    +0.05
    0.5%
    159
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.05
    0.01
    406
    +0.05
    0.01
    241
    +0.05
    0.01
    Negative Logits
    gaard
    -0.39
    rano
    -0.38
    halla
    -0.37
     Aval
    -0.36
    kaya
    -0.35
    regon
    -0.33
    awaru
    -0.32
    haul
    -0.32
    hement
    -0.32
     melanch
    -0.31
    POSITIVE LOGITS
    IG
    0.40
    IB
    0.40
    RN
    0.39
    INT
    0.39
    ISS
    0.39
    IT
    0.37
    AG
    0.36
    IK
    0.36
    U
    0.35
    AC
    0.35
    Activations Density 0.007%

    No Known Activations