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 6144
    5. 8-RES_FS6144-JB
    6. 4536
    Prev
    Next
    INDEX
    Explanations

    personal experiences and expressions of gratitude

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    362
    +0.11
    0.5%
    626
    +0.10
    0.5%
    94
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.10
    567
    +0.10
    0.06
    608
    +0.09
    0.09
    Negative Logits
    ucket
    -0.76
    chester
    -0.73
    lette
    -0.70
    hound
    -0.64
    bay
    -0.63
    ãĥĺ
    -0.62
    gee
    -0.62
    glers
    -0.61
    cone
    -0.60
    thood
    -0.60
    POSITIVE LOGITS
     thoughts
    1.22
     findings
    1.15
     grievances
    1.11
     secrets
    1.06
     frustrations
    1.06
     displeasure
    1.01
     sentiments
    0.99
     feelings
    0.99
     truths
    0.96
     ideas
    0.93
    Activations Density 0.942%

    No Known Activations