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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23860
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with various bandwidth specifications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    583
    +0.11
    0.5%
    98
    +0.10
    0.4%
    379
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.11
    0.04
    230
    +0.10
    0.04
    298
    +0.09
    0.03
    Negative Logits
    warts
    -0.75
    agan
    -0.69
     symmetry
    -0.66
    ugal
    -0.65
    verend
    -0.64
    ancing
    -0.64
    udic
    -0.63
    etheless
    -0.62
    akia
    -0.62
    swick
    -0.62
    POSITIVE LOGITS
     MHz
    0.94
    MHz
    0.88
    mAh
    0.84
    XL
    0.83
     Mile
    0.82
    000
    0.81
    Hz
    0.81
    0002
    0.81
    +
    0.81
    cc
    0.80
    Activations Density 0.062%

    No Known Activations