Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 12165
    Prev
    Next
    INDEX
    Explanations

    expressions related to distance or movement

    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
    589
    +0.10
    0.4%
    702
    +0.09
    0.4%
    727
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.10
    0.02
    553
    +0.09
    0.01
    702
    +0.09
    0.01
    Negative Logits
    uala
    -0.83
    Gi
    -0.74
    ©¶æ
    -0.73
    BIL
    -0.73
    mA
    -0.67
    lance
    -0.67
    illation
    -0.63
    Ca
    -0.62
    CVE
    -0.61
    PLA
    -0.60
    POSITIVE LOGITS
    sighted
    0.91
    fetched
    0.84
    reaching
    0.81
     distances
    0.74
    range
    0.74
     than
    0.72
    endars
    0.71
    outheast
    0.69
    field
    0.69
    upt
    0.69
    Activations Density 0.044%

    No Known Activations