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 3072
    5. 8-RES_FS3072-JB
    6. 2448
    Prev
    Next
    INDEX
    Explanations

    mentions of death-related topics, including death penalty cases, executions, murder, and mortality

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    319
    +0.11
    0.5%
    288
    +0.10
    0.5%
    203
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.08
    132
    +0.10
    0.06
    319
    +0.10
    0.06
    Negative Logits
    Cola
    -0.86
    CN
    -0.75
    EEK
    -0.74
    kef
    -0.72
    toe
    -0.72
    CRE
    -0.71
    umar
    -0.69
    GB
    -0.68
    ĸļ
    -0.68
    oS
    -0.66
    POSITIVE LOGITS
     procession
    0.96
     penalty
    0.92
     rites
    0.92
     toll
    0.92
    blow
    0.88
    guard
    0.86
     thro
    0.86
    adder
    0.85
    stroke
    0.84
     shroud
    0.84
    Activations Density 0.689%

    No Known Activations