© 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. 1361
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical wars, particularly World War II

    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
    288
    +0.12
    0.6%
    246
    +0.09
    0.4%
    150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.12
    0.02
    384
    +0.09
    0.02
    146
    +0.09
    0.02
    Negative Logits
    OGR
    -0.79
    obook
    -0.72
    ITY
    -0.69
    */(
    -0.69
    Asset
    -0.66
     metab
    -0.62
     snipp
    -0.62
    iquid
    -0.62
     KE
    -0.60
     answ
    -0.60
    POSITIVE LOGITS
     II
    0.99
    lords
    0.98
    lord
    0.97
     III
    0.90
    bler
    0.84
    planes
    0.82
    ombat
    0.80
    rior
    0.78
    riors
    0.78
    rington
    0.74
    Activations Density 0.058%

    No Known Activations