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

    Neuronpedia

    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. 2143
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    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
    481
    +0.14
    0.6%
    556
    +0.12
    0.6%
    237
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.14
    0.04
    193
    +0.12
    0.04
    288
    +0.11
    0.05
    Negative Logits
    Adapt
    -0.78
    ERG
    -0.74
    GoldMagikarp
    -0.70
    natureconservancy
    -0.69
    Page
    -0.67
    prototype
    -0.66
    Cooldown
    -0.65
    ãģį
    -0.64
    Cache
    -0.64
    æĪ¦
    -0.64
    POSITIVE LOGITS
     onwards
    0.95
     backgrounds
    0.87
     standpoint
    0.82
     onward
    0.80
     onto
    0.73
     fame
    0.70
     Indies
    0.70
     perspective
    0.69
     residing
    0.68
     converge
    0.67
    Activations Density 0.225%

    No Known Activations