© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 16254
    Prev
    Next
    INDEX
    Explanations

    financial terms and records

    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
    208
    +0.12
    0.5%
    575
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.12
    0.01
    22
    +0.10
    0.01
    159
    +0.10
    0.01
    Negative Logits
    âĸ¬âĸ¬
    -0.81
    footed
    -0.80
    ball
    -0.73
    âĸ¬
    -0.72
     respons
    -0.66
    BOOK
    -0.65
    BALL
    -0.65
     thumbs
    -0.65
    ãĥ£
    -0.64
    MET
    -0.63
    POSITIVE LOGITS
    onential
    1.58
    ansion
    1.53
    onent
    1.41
    ulsion
    1.40
    anded
    1.38
    anding
    1.34
    osed
    1.33
    ression
    1.31
    ressive
    1.23
    ressed
    1.22
    Activations Density 0.010%

    No Known Activations