© 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. 8876
    Prev
    Next
    INDEX
    Explanations

    keywords related to political figures and controversial actions or statements

    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
    288
    +0.14
    0.6%
    538
    +0.10
    0.5%
    232
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.01
    538
    +0.10
    0.01
    659
    +0.10
    0.01
    Negative Logits
    ACTED
    -0.69
     occup
    -0.68
    PDATE
    -0.66
     carriers
    -0.66
     easing
    -0.63
     explosives
    -0.63
     Overwatch
    -0.61
     pref
    -0.60
     alpha
    -0.60
     ultrasound
    -0.59
    POSITIVE LOGITS
    ict
    1.05
    inas
    1.00
    ildo
    0.98
    enture
    0.97
    isson
    0.96
    onna
    0.96
    illon
    0.94
    iral
    0.94
    itto
    0.92
    illian
    0.92
    Activations Density 0.020%

    No Known Activations