© 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 12288
    9. 8-RES_FS12288-JB
    11. 420
    Prev
    Next
    INDEX
    Explanations

    word pairs related to excitement or attention

    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
    314
    +0.15
    0.7%
    288
    +0.13
    0.6%
    271
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.15
    0.02
    326
    +0.13
    0.02
    288
    +0.10
    0.02
    Negative Logits
     restitution
    -0.70
    tein
    -0.70
    izations
    -0.70
     dedication
    -0.65
    isations
    -0.64
     extrem
    -0.62
     antit
    -0.62
    ©¶æ
    -0.62
    hibition
    -0.61
     Lak
    -0.60
    POSITIVE LOGITS
    saw
    1.28
    feed
    1.07
    worthy
    1.04
    words
    1.02
    word
    0.97
    arded
    0.96
    oola
    0.92
    aic
    0.90
    ards
    0.89
    iest
    0.88
    Activations Density 0.092%

    No Known Activations