© 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 24576
    5. 8-RES_FS24576-JB
    6. 2078
    Prev
    Next
    INDEX
    Explanations

    descriptions of incidents involving crime or tragedy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    481
    +0.40
    1.9%
    378
    +0.10
    0.5%
    570
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.40
    0.08
    570
    +0.10
    0.02
    481
    +0.10
    0.08
    Negative Logits
    pmwiki
    -0.76
    Son
    -0.70
    icho
    -0.69
    Weather
    -0.65
    Nusra
    -0.65
    Hyp
    -0.65
    rov
    -0.64
    Yan
    -0.63
    Organ
    -0.62
    Angel
    -0.61
    POSITIVE LOGITS
    Ħ¢
    0.80
     offending
    0.76
     afore
    0.73
     warr
    0.69
     entire
    0.66
     goodies
    0.64
     legitimately
    0.62
     workplace
    0.62
     bolted
    0.60
     unres
    0.60
    Activations Density 0.881%

    No Known Activations