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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 438
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.20
    0.9%
    659
    +0.18
    0.9%
    484
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.20
    0.20
    314
    +0.18
    0.04
    67
    +0.09
    0.09
    Negative Logits
     bottleneck
    -0.76
     Pry
    -0.71
     Zur
    -0.70
     formerly
    -0.68
     pleasure
    -0.68
     aging
    -0.68
     transports
    -0.68
     bypass
    -0.66
     Geral
    -0.65
     bones
    -0.65
    POSITIVE LOGITS
    OT
    1.38
    UR
    1.29
    AD
    1.29
    AM
    1.28
    BS
    1.25
    AS
    1.24
    OU
    1.23
    ILL
    1.23
    OC
    1.22
    PS
    1.22
    Activations Density 0.875%

    No Known Activations