© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19961
    Prev
    Next
    INDEX
    Explanations

    dates and specific events or accomplishments

    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
    480
    +0.45
    2.3%
    447
    +0.19
    1.0%
    266
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.45
    0.02
    266
    +0.19
    0.07
    499
    +0.13
    0.04
    Negative Logits
    selves
    -0.68
     theirs
    -0.65
    OTAL
    -0.64
    each
    -0.64
    Change
    -0.62
     ted
    -0.61
    them
    -0.60
     selves
    -0.57
    omever
    -0.56
    >.
    -0.56
    POSITIVE LOGITS
     Originally
    0.61
     renown
    0.58
     renowned
    0.57
     Featured
    0.56
     underrated
    0.56
     ATK
    0.56
     Joined
    0.55
     âĵĺ
    0.55
     versatile
    0.54
     RHP
    0.53
    Activations Density 0.642%

    No Known Activations