© 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. 18187
    Prev
    Next
    INDEX
    Explanations

    the name "Salman" in a document

    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
    447
    +0.13
    0.6%
    186
    +0.12
    0.5%
    699
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.03
    326
    +0.12
    0.03
    659
    +0.10
    0.02
    Negative Logits
    rights
    -0.87
    lem
    -0.86
    bre
    -0.83
    fulness
    -0.83
    ptive
    -0.81
    plex
    -0.80
    vil
    -0.79
    cle
    -0.77
    liest
    -0.77
    ãĥ£
    -0.76
    POSITIVE LOGITS
    ary
    0.78
     Mehran
    0.76
     Cooperation
    0.74
    ocity
    0.71
    arity
    0.68
    isted
    0.67
    ists
    0.65
    NOW
    0.63
     drafts
    0.63
    OUGH
    0.62
    Activations Density 0.077%

    No Known Activations