© 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. 19610
    Prev
    Next
    INDEX
    Explanations

    references to roles, actions, and situations in sports

    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
    398
    +0.14
    0.7%
    568
    +0.12
    0.6%
    481
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.08
    575
    +0.12
    0.06
    225
    +0.12
    0.05
    Negative Logits
    uga
    -0.84
    ãĥĥãĥī
    -0.81
    donald
    -0.75
    Birth
    -0.74
    cair
    -0.74
    £ı
    -0.72
    soDeliveryDate
    -0.71
    meet
    -0.70
    Newsletter
    -0.70
    ãĤ¨ãĥ«
    -0.69
    POSITIVE LOGITS
     routines
    0.67
     brigade
    0.64
     extraord
    0.63
     Berman
    0.60
     cue
    0.59
     interpreter
    0.59
     fiasco
    0.58
     mentality
    0.57
     repertoire
    0.57
     selector
    0.57
    Activations Density 0.423%

    No Known Activations