© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 7396
    Prev
    Next
    INDEX
    Explanations

    phrases related to political discussions and decision-making

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    +0.33
    1.7%
    480
    +0.32
    1.7%
    447
    +0.18
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.33
    0.10
    481
    +0.32
    0.11
    385
    +0.18
    0.08
    Negative Logits
     whilst
    -1.05
    Firstly
    -0.89
     Whilst
    -0.84
    !".
    -0.82
     haha
    -0.75
    ãĥİ
    -0.74
     util
    -0.73
    ´
    -0.73
    ".[
    -0.72
     afterwards
    -0.72
    POSITIVE LOGITS
     plaintiffs
    0.92
     nonprofits
    0.89
     Grassley
    0.89
     lawmakers
    0.89
     statewide
    0.85
     nonprofit
    0.83
     federal
    0.82
     attorneys
    0.82
     POLITICO
    0.81
     DeVos
    0.80
    Activations Density 1.546%

    No Known Activations