© 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. 41766
    Prev
    Next
    INDEX
    Explanations

    instances of the word "surveillance" and its variations

    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
    430
    +0.10
    0.5%
    104
    +0.09
    0.4%
    713
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    654
    +0.10
    0.01
    404
    +0.09
    0.01
    713
    +0.09
    0.01
    Negative Logits
     Kinnikuman
    -0.67
     brains
    -0.64
     perspective
    -0.64
    tz
    -0.58
     fields
    -0.57
    behind
    -0.57
     Sachs
    -0.57
    ativity
    -0.56
     Hughes
    -0.56
     Maxwell
    -0.56
    POSITIVE LOGITS
    illance
    0.78
    Downloadha
    0.75
    âĶĢâĶĢâĶĢâĶĢ
    0.71
    uber
    0.69
    illes
    0.69
    pecting
    0.68
     COURT
    0.66
    imate
    0.66
    ibaba
    0.65
    xual
    0.65
    Activations Density 0.009%

    No Known Activations