© 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 49152
    9. 8-RES_FS49152-JB
    11. 25780
    Prev
    Next
    INDEX
    Explanations

    specific technical and operational details related to devices, services, and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.36
    1.8%
    447
    +0.21
    1.0%
    481
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.36
    0.08
    652
    +0.21
    0.05
    480
    +0.15
    0.00
    Negative Logits
    etheless
    -0.71
    ¿½
    -0.58
    evin
    -0.58
    ©¶æ¥µ
    -0.58
    ornings
    -0.57
    VERTISEMENT
    -0.57
    entimes
    -0.56
     srf
    -0.56
    ĻĤ
    -0.54
    ielding
    -0.54
    POSITIVE LOGITS
    iest
    0.95
    liest
    0.87
     portion
    0.85
     version
    0.76
     equivalent
    0.69
    hest
    0.69
     logo
    0.67
    same
    0.64
    prints
    0.64
     alphabet
    0.64
    Activations Density 0.374%

    No Known Activations