© 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. 45521
    Prev
    Next
    INDEX
    Explanations

    commands or phrases that urge cessation or stopping an action

    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
    86
    +0.12
    0.5%
    71
    +0.12
    0.5%
    351
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.12
    0.02
    557
    +0.12
    0.02
    764
    +0.10
    0.02
    Negative Logits
    Sov
    -0.86
    Versions
    -0.77
    orthy
    -0.71
    aceae
    -0.69
     amph
    -0.68
    eer
    -0.67
    ighth
    -0.66
    rium
    -0.65
    ieth
    -0.65
    esses
    -0.64
    POSITIVE LOGITS
     bothering
    1.20
     worrying
    1.08
     wasting
    1.05
     whining
    1.01
     raining
    0.92
    watching
    0.92
     blaming
    0.92
     pretending
    0.91
     messing
    0.89
     interfering
    0.88
    Activations Density 0.020%

    No Known Activations