© 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 49152
    9. 8-RES_FS49152-JB
    11. 37410
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the importance of audience engagement and interactive communication in a presentation

    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
    214
    +0.11
    0.5%
    678
    +0.11
    0.5%
    369
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.11
    0.02
    159
    +0.11
    0.02
    567
    +0.10
    0.02
    Negative Logits
    ãĥĻ
    -0.65
    TED
    -0.63
     Notting
    -0.62
    ravis
    -0.61
    VEN
    -0.61
    ãĤ¬
    -0.61
    govtrack
    -0.60
    olate
    -0.60
     Pru
    -0.60
    çī
    -0.59
    POSITIVE LOGITS
     unrestricted
    1.03
     unlimited
    0.87
     flexibility
    0.86
     exceptions
    0.85
     access
    0.84
     freely
    0.78
     deduction
    0.75
     slip
    0.75
     lapse
    0.75
    parency
    0.74
    Activations Density 0.119%

    No Known Activations