© 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. 26574
    Prev
    Next
    INDEX
    Explanations

    phrases expressing denial or negation of statements

    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
    674
    +0.10
    0.5%
    353
    +0.10
    0.5%
    378
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.10
    0.01
    243
    +0.10
    0.02
    566
    +0.09
    0.01
    Negative Logits
     culminated
    -0.66
    kinson
    -0.64
     culmin
    -0.63
    icipated
    -0.62
     culminating
    -0.61
    adelphia
    -0.60
    itary
    -0.60
    iphany
    -0.58
     littered
    -0.58
    ilation
    -0.57
    POSITIVE LOGITS
     Nope
    0.74
    nor
    0.70
    大
    0.65
    èĪ
    0.65
     Saud
    0.64
     nor
    0.64
    çĶ°
    0.63
    SPA
    0.63
    å¾
    0.62
    ItemImage
    0.61
    Activations Density 0.049%

    No Known Activations