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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 846
    Prev
    Next
    INDEX
    Explanations

    financial and business-related terms

    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
    481
    +0.17
    0.8%
    249
    +0.12
    0.6%
    234
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    714
    +0.17
    0.04
    384
    +0.12
    0.04
    393
    +0.09
    0.06
    Negative Logits
    scribe
    -0.79
    enth
    -0.78
    wark
    -0.76
    oti
    -0.74
    acers
    -0.73
    ajor
    -0.73
    agle
    -0.72
    alion
    -0.71
    instance
    -0.70
    uma
    -0.69
    POSITIVE LOGITS
     lack
    1.27
     penchant
    1.25
     inability
    1.25
     willingness
    1.13
     unwillingness
    1.11
     cumbers
    1.11
     propensity
    1.11
     reluctance
    1.05
     sluggish
    1.04
     lackluster
    1.03
    Activations Density 0.281%

    No Known Activations