© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12295
    Prev
    Next
    INDEX
    Explanations

    words related to detecting or finding clues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    99
    +0.13
    0.6%
    223
    +0.11
    0.5%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    641
    +0.13
    0.02
    705
    +0.11
    0.01
    99
    +0.10
    0.01
    Negative Logits
    ategory
    -0.83
    oslav
    -0.70
    rior
    -0.68
    atism
    -0.68
    fare
    -0.66
    kus
    -0.64
    rifice
    -0.62
     neighb
    -0.62
    È
    -0.61
    lav
    -0.60
    POSITIVE LOGITS
     clue
    1.16
     hint
    1.14
     clues
    1.10
     hints
    0.98
     glean
    0.95
    tale
    0.71
     illuminate
    0.70
     pointing
    0.70
     glimps
    0.69
    ibly
    0.69
    Activations Density 0.033%

    No Known Activations