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 768
    5. 8-RES_FS768-JB
    6. 48
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal matters and policies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    102
    +0.12
    0.5%
    55
    +0.11
    0.5%
    159
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.12
    233
    +0.11
    0.09
    393
    +0.11
    0.13
    Negative Logits
    okia
    -0.87
    EStream
    -0.85
    ESE
    -0.85
    ETS
    -0.84
    asio
    -0.82
    iage
    -0.80
    SHIP
    -0.79
    ICES
    -0.78
    PsyNetMessage
    -0.78
    YS
    -0.76
    POSITIVE LOGITS
     adventurous
    1.11
     economical
    1.10
     technologically
    1.07
     unpredictable
    1.06
     pragmatic
    1.05
     flavorful
    1.03
     uncomp
    1.03
     imaginative
    1.03
     efficient
    1.03
     durable
    1.03
    Activations Density 3.411%

    No Known Activations