© 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 49152
    9. 8-RES_FS49152-JB
    11. 26571
    Prev
    Next
    INDEX
    Explanations

    references to automotive manufacturers, specifically General Motors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    288
    +0.15
    0.7%
    685
    +0.10
    0.5%
    351
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.15
    0.01
    682
    +0.10
    0.01
    685
    +0.10
    0.01
    Negative Logits
    lihood
    -0.84
    gery
    -0.70
    çĦ
    -0.67
    glers
    -0.65
    gently
    -0.63
     judges
    -0.60
    ydia
    -0.60
    ĺħ
    -0.60
    lier
    -0.59
    èª
    -0.59
    POSITIVE LOGITS
    ports
    1.22
    pring
    1.02
    bourg
    0.90
    wagen
    0.87
    puter
    0.84
    negie
    0.82
     Corporation
    0.81
    otive
    0.79
     Racing
    0.76
    obiles
    0.74
    Activations Density 0.005%

    No Known Activations