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. 8352
    Prev
    Next
    INDEX
    Explanations

    terms related to physical attacks or conflicts

    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
    447
    +0.14
    0.6%
    740
    +0.11
    0.5%
    486
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.14
    0.02
    486
    +0.11
    0.02
    553
    +0.11
    0.02
    Negative Logits
    mad
    -0.80
    zl
    -0.73
    soDeliveryDate
    -0.73
    rigan
    -0.70
    trap
    -0.70
    gio
    -0.69
    clips
    -0.69
    fried
    -0.68
    vation
    -0.68
    ser
    -0.68
    POSITIVE LOGITS
     unsuspecting
    0.76
     furiously
    0.74
     anew
    0.74
     indiscrim
    0.72
     them
    0.71
     relentlessly
    0.70
     vigorously
    0.68
     him
    0.66
     havoc
    0.64
     vulnerable
    0.64
    Activations Density 0.059%

    No Known Activations