© 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. 31577
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal disputes and potential consequences

    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
    +0.13
    0.6%
    530
    +0.10
    0.5%
    334
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    676
    +0.13
    0.11
    307
    +0.10
    0.07
    460
    +0.10
    0.08
    Negative Logits
     Patriarch
    -0.74
     Britt
    -0.55
    nie
    -0.54
     Bret
    -0.54
     RD
    -0.54
    rounder
    -0.53
     Bapt
    -0.53
     Duff
    -0.53
    GI
    -0.52
     Bert
    -0.51
    POSITIVE LOGITS
    xus
    0.76
     intersections
    0.75
    ////////////////////////////////
    0.72
    ulkan
    0.72
    uble
    0.71
    llah
    0.69
     guiActiveUn
    0.69
    obiles
    0.68
    ħĭ
    0.68
    Footnote
    0.68
    Activations Density 9.030%

    No Known Activations