© 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. 41620
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to the economic benefits and job creation associated with legislative changes or industry actions

    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
    459
    +0.11
    0.5%
    558
    +0.11
    0.5%
    413
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.11
    0.04
    724
    +0.11
    0.04
    529
    +0.10
    0.03
    Negative Logits
     Bloody
    -0.71
    olog
    -0.69
     coward
    -0.68
    mut
    -0.67
     ling
    -0.66
     veil
    -0.66
    password
    -0.65
     fault
    -0.65
     messed
    -0.64
     blindly
    -0.64
    POSITIVE LOGITS
    ONSORED
    1.04
     coffers
    1.01
     revenue
    0.95
    ificantly
    0.92
     prosperity
    0.91
     revenues
    0.88
     taxp
    0.85
     tourism
    0.84
     multiplier
    0.83
    arbon
    0.83
    Activations Density 0.215%

    No Known Activations