© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 24015
    Prev
    Next
    INDEX
    Explanations

    expressions related to urgency or necessity

    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
    222
    +0.10
    0.5%
    741
    +0.10
    0.4%
    482
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    222
    +0.10
    0.01
    408
    +0.10
    0.01
    479
    +0.10
    0.01
    Negative Logits
    adelphia
    -0.86
    creen
    -0.75
    wife
    -0.75
    ells
    -0.74
    alid
    -0.73
    claimer
    -0.72
    dor
    -0.71
    aters
    -0.70
    imore
    -0.70
    atever
    -0.69
    POSITIVE LOGITS
     attention
    1.11
     corrective
    0.87
     transparency
    0.86
     reinforcements
    0.84
     improvement
    0.83
     scrutiny
    0.83
     antidote
    0.81
     halt
    0.80
     overhaul
    0.79
     applause
    0.78
    Activations Density 0.016%

    No Known Activations