© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32011
    Prev
    Next
    INDEX
    Explanations

    legal and political terms or issues

    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
    481
    +0.15
    0.7%
    458
    +0.10
    0.5%
    718
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.15
    0.32
    679
    +0.10
    0.23
    283
    +0.10
    -0.01
    Negative Logits
    oad
    -0.81
    throp
    -0.73
    âķIJâķIJ
    -0.71
    robe
    -0.66
    llan
    -0.66
    oaded
    -0.64
    onga
    -0.63
    ffen
    -0.62
    haw
    -0.62
    aunder
    -0.61
    POSITIVE LOGITS
     plag
    0.93
     arise
    0.86
     arising
    0.85
     unresolved
    0.81
     arises
    0.74
     affecting
    0.74
     arisen
    0.73
     worsened
    0.71
     escalated
    0.70
     resolved
    0.70
    Activations Density 15.987%

    No Known Activations