© 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 24576
    9. 8-RES_FS24576-JB
    11. 19400
    Prev
    Next
    INDEX
    Explanations

    references to official reports or publications

    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
    91
    +0.11
    0.5%
    339
    +0.10
    0.5%
    446
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.11
    0.06
    288
    +0.10
    0.07
    680
    +0.09
    0.03
    Negative Logits
     oneself
    -0.87
    uador
    -0.81
     herself
    -0.77
    skirts
    -0.76
    rogens
    -0.75
    ocent
    -0.74
    cair
    -0.73
     himself
    -0.70
     Yourself
    -0.69
     myself
    -0.68
    POSITIVE LOGITS
     headquarters
    1.11
     portfolio
    1.09
     division
    1.05
     counterpart
    1.02
     counterparts
    1.02
     holdings
    1.01
     foray
    1.01
     lineup
    0.99
     mascot
    0.97
     affiliate
    0.97
    Activations Density 0.441%

    No Known Activations