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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9925
    Prev
    Next
    INDEX
    Explanations

    references to "open" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    96
    +0.10
    0.4%
    240
    +0.10
    0.4%
    535
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.10
    0.03
    240
    +0.10
    0.03
    96
    +0.09
    0.03
    Negative Logits
    iage
    -0.73
    ibur
    -0.67
     Commando
    -0.65
    CTV
    -0.64
     Marketable
    -0.61
    rior
    -0.59
    yz
    -0.59
     Monstrous
    -0.58
    older
    -0.58
     Witches
    -0.58
    POSITIVE LOGITS
     minded
    0.95
    hearted
    0.87
    ended
    0.85
    street
    0.80
    ource
    0.78
    handed
    0.77
     doors
    0.76
     eyed
    0.75
     source
    0.75
     invitation
    0.74
    Activations Density 0.062%

    No Known Activations