© 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. 37293
    Prev
    Next
    INDEX
    Explanations

    instances of the word "chair" and its variations related to leadership positions

    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
    314
    +0.15
    0.7%
    167
    +0.12
    0.6%
    679
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.15
    0.01
    691
    +0.12
    0.01
    463
    +0.12
    0.01
    Negative Logits
     IMAGES
    -0.84
     suscept
    -0.65
     tatt
    -0.64
     Ultron
    -0.62
     condu
    -0.61
     DATA
    -0.61
     blackmail
    -0.60
     circumst
    -0.59
     Curve
    -0.58
     Keynes
    -0.58
    POSITIVE LOGITS
    woman
    1.52
    manship
    1.41
    person
    1.39
    lift
    1.21
    women
    1.19
    mans
    1.16
    men
    1.13
    boards
    1.10
    pers
    1.08
    holder
    1.04
    Activations Density 0.009%

    No Known Activations