© 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. 1301
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions or news 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
    756
    +0.13
    0.6%
    639
    +0.11
    0.5%
    478
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.13
    -0.04
    570
    +0.11
    0.02
    711
    +0.10
    0.04
    Negative Logits
    Picture
    -0.56
    ensional
    -0.55
     spoilers
    -0.50
    Adds
    -0.49
     congratulations
    -0.49
    tackle
    -0.49
     Originally
    -0.48
    Spoiler
    -0.48
    esides
    -0.47
    ajor
    -0.47
    POSITIVE LOGITS
    )).
    0.88
    ).[
    0.85
    ))))
    0.78
     thereafter
    0.75
     thereto
    0.74
    ]."
    0.73
     etc
    0.72
     accordingly
    0.71
     thereof
    0.70
    )."
    0.70
    Activations Density 2.972%

    No Known Activations