© 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. 23906
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered 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
    408
    +0.11
    0.5%
    7
    +0.11
    0.5%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.04
    455
    +0.11
    0.04
    7
    +0.11
    0.03
    Negative Logits
    stre
    -0.70
    FIG
    -0.69
    ilation
    -0.68
     Slowly
    -0.66
    soon
    -0.65
     Initially
    -0.61
    NOT
    -0.59
     cautiously
    -0.59
    lie
    -0.59
    sometimes
    -0.59
    POSITIVE LOGITS
     anymore
    0.99
     recourse
    0.95
     enough
    0.94
     any
    0.89
     sufficient
    0.89
    stood
    0.88
     permission
    0.88
     adequate
    0.85
     access
    0.81
     anything
    0.81
    Activations Density 0.070%

    No Known Activations