© 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. 19335
    Prev
    Next
    INDEX
    Explanations

    information related to investigative reports on various incidents

    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
    139
    +0.12
    0.5%
    393
    +0.10
    0.5%
    515
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    139
    +0.12
    0.09
    259
    +0.10
    0.07
    571
    +0.10
    0.07
    Negative Logits
    Priv
    -0.69
     Spending
    -0.66
    dding
    -0.64
     Saying
    -0.63
     Jaw
    -0.63
     Coral
    -0.61
    SHARE
    -0.60
     Polk
    -0.60
     Credits
    -0.59
    friends
    -0.59
    POSITIVE LOGITS
    alian
    1.13
     becomes
    1.11
     disappears
    1.10
     appears
    1.09
     occurs
    1.07
     happened
    1.06
     occurred
    1.05
     exists
    1.05
     belongs
    1.05
    unes
    1.04
    Activations Density 0.282%

    No Known Activations