© 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. 37354
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms associated with government and political contexts

    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
    481
    +0.11
    0.5%
    701
    +0.11
    0.5%
    239
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.11
    0.03
    406
    +0.11
    0.03
    659
    +0.10
    0.02
    Negative Logits
    raising
    -0.76
     sidx
    -0.72
    eatures
    -0.68
     Columb
    -0.64
    :{
    -0.61
     rud
    -0.61
    ï¸
    -0.61
    Interstitial
    -0.60
    scl
    -0.60
     withd
    -0.60
    POSITIVE LOGITS
    idia
    0.79
    zsche
    0.74
    arious
    0.74
    ukong
    0.69
    onsense
    0.67
    imil
    0.66
    theless
    0.66
    isance
    0.66
    ictionary
    0.65
    anyahu
    0.65
    Activations Density 0.064%

    No Known Activations