© 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. 416
    Prev
    Next
    INDEX
    Explanations

    company names

    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
    481
    +0.13
    0.6%
    80
    +0.10
    0.4%
    68
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.09
    232
    +0.10
    0.07
    145
    +0.10
    0.07
    Negative Logits
     trope
    -0.94
     recess
    -0.86
     impe
    -0.80
     joking
    -0.79
     override
    -0.78
     mentally
    -0.77
     poem
    -0.77
     characteristic
    -0.76
     filibuster
    -0.76
     disorder
    -0.75
    POSITIVE LOGITS
    Shares
    1.34
     Holdings
    1.25
    Soft
    1.18
     Ventures
    1.13
    FX
    1.12
    ibur
    1.11
     Corp
    1.09
    isoft
    1.07
     Labs
    1.07
     Technologies
    1.05
    Activations Density 0.608%

    No Known Activations