© 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 12288
    9. 8-RES_FS12288-JB
    11. 10142
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or positive events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    459
    +0.13
    0.6%
    151
    +0.11
    0.5%
    144
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.03
    144
    +0.11
    0.03
    381
    +0.10
    0.03
    Negative Logits
    arin
    -0.82
    soDeliveryDate
    -0.78
    DoS
    -0.77
    iban
    -0.76
    urally
    -0.71
    ngth
    -0.70
    dor
    -0.68
    lege
    -0.68
    Rush
    -0.67
    çīĪ
    -0.66
    POSITIVE LOGITS
     birthday
    0.85
     endings
    0.85
     Meal
    0.84
     Birthday
    0.77
    vale
    0.71
    istic
    0.70
     happily
    0.68
     stroll
    0.68
    ness
    0.68
     Mondays
    0.67
    Activations Density 0.088%

    No Known Activations