© 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. 19567
    Prev
    Next
    INDEX
    Explanations

    references to Sharia law

    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
    525
    +0.13
    0.6%
    549
    +0.10
    0.5%
    168
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    525
    +0.13
    0.01
    588
    +0.10
    0.01
    475
    +0.10
    0.01
    Negative Logits
    REDACTED
    -0.72
    ername
    -0.68
     Upton
    -0.65
    GROUND
    -0.64
    asus
    -0.64
     Uran
    -0.64
    insula
    -0.63
    CRIP
    -0.63
    é¾įå¥ij士
    -0.63
    ortium
    -0.62
    POSITIVE LOGITS
    ples
    1.24
    pton
    1.22
    pling
    1.15
    ãĥ£
    1.13
    ply
    1.01
    jah
    1.01
    riors
    0.99
    pless
    0.99
    ning
    0.96
    pering
    0.94
    Activations Density 0.011%

    No Known Activations