© 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 49152
    9. 8-RES_FS49152-JB
    11. 41759
    Prev
    Next
    INDEX
    Explanations

    references to Intel and its products

    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
    343
    +0.14
    0.7%
    288
    +0.14
    0.7%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.02
    220
    +0.14
    0.01
    146
    +0.10
    0.01
    Negative Logits
    gery
    -0.82
    pee
    -0.75
    iatrics
    -0.74
    bish
    -0.71
     Rowling
    -0.70
    pees
    -0.69
     undone
    -0.68
     empt
    -0.67
    rouse
    -0.67
    glers
    -0.67
    POSITIVE LOGITS
    ®
    0.90
     Xeon
    0.89
    iture
    0.89
     Corporation
    0.87
     Labs
    0.87
     Extreme
    0.84
     processors
    0.83
     CPUs
    0.79
    Performance
    0.77
     Core
    0.75
    Activations Density 0.004%

    No Known Activations