© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 19382
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political issues

    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
    314
    +0.14
    0.7%
    496
    +0.12
    0.5%
    650
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.14
    0.07
    650
    +0.12
    0.07
    675
    +0.10
    0.07
    Negative Logits
     clitor
    -0.81
     pigeon
    -0.75
     reflex
    -0.73
     targeted
    -0.72
     couch
    -0.71
     leaps
    -0.71
     spir
    -0.71
     indo
    -0.70
     mount
    -0.70
     barg
    -0.70
    POSITIVE LOGITS
    ï¸ı
    1.42
    ï¸
    1.01
    ternity
    0.98
    uthor
    0.88
    Previously
    0.86
    Reason
    0.86
    \/\/
    0.85
    Discuss
    0.85
    RELATED
    0.84
    Roberts
    0.83
    Activations Density 0.149%

    No Known Activations