© 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. 19418
    Prev
    Next
    INDEX
    Explanations

    instructions or technical details related to wiring and physical connections

    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
    88
    +0.12
    0.5%
    236
    +0.10
    0.5%
    130
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.12
    0.07
    88
    +0.10
    0.06
    225
    +0.10
    0.06
    Negative Logits
    exclusive
    -0.67
    \":
    -0.62
    pard
    -0.61
    én
    -0.59
    product
    -0.58
    iculty
    -0.55
    staking
    -0.55
    Jew
    -0.54
    ensional
    -0.53
    odcast
    -0.53
    POSITIVE LOGITS
     etc
    1.40
    ,...
    1.01
    ?,
    0.92
    !,
    0.80
     ect
    0.78
     respectively
    0.74
     blah
    0.72
    ,,
    0.70
    (),
    0.69
     };
    0.69
    Activations Density 0.687%

    No Known Activations