© 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. 37398
    Prev
    Next
    INDEX
    Explanations

    phrases expressing requests or encouragement for engagement and support

    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
    373
    +0.13
    0.7%
    383
    +0.11
    0.6%
    732
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.13
    0.01
    125
    +0.11
    0.01
    666
    +0.11
    0.01
    Negative Logits
     nonetheless
    -0.66
     hindsight
    -0.65
    glers
    -0.63
     runes
    -0.62
    panic
    -0.62
     Sapp
    -0.61
    iter
    -0.61
     paraph
    -0.60
    reek
    -0.59
    clusions
    -0.59
    POSITIVE LOGITS
    bleacher
    0.66
    ACY
    0.65
    vice
    0.62
    iphate
    0.59
    yll
    0.57
    atered
    0.57
     wellbeing
    0.56
    cellence
    0.56
    ONSORED
    0.55
    Ĵ
    0.54
    Activations Density 0.018%

    No Known Activations