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

    Neuronpedia

    Jacobian LensNEW
    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 49152
    9. 8-RES_FS49152-JB
    11. 43482
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "broadcast."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.15
    0.7%
    484
    +0.12
    0.6%
    481
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.15
    0.02
    540
    +0.12
    0.02
    288
    +0.12
    0.01
    Negative Logits
    urat
    -0.84
    illard
    -0.75
    uana
    -0.71
    ortium
    -0.71
    onne
    -0.71
     Buchanan
    -0.68
     assum
    -0.67
    anova
    -0.67
    cule
    -0.65
    ucket
    -0.65
    POSITIVE LOGITS
     broadcast
    1.00
     broadcasts
    0.94
     Broadcast
    0.91
     booth
    0.91
    casters
    0.90
     playback
    0.90
     broadcaster
    0.88
     broadcasting
    0.87
     television
    0.86
     announcer
    0.85
    Activations Density 0.015%

    No Known Activations