© 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 49152
    9. 8-RES_FS49152-JB
    11. 37447
    Prev
    Next
    INDEX
    Explanations

    references to geographical origins or hometowns of individuals

    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
    668
    +0.11
    0.5%
    193
    +0.11
    0.5%
    424
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.11
    0.02
    302
    +0.11
    0.02
    506
    +0.10
    0.02
    Negative Logits
    arcity
    -0.79
    operation
    -0.70
    tein
    -0.68
    emin
    -0.67
    evidence
    -0.66
    usters
    -0.65
     usefulness
    -0.65
    direction
    -0.65
     procession
    -0.64
    saf
    -0.64
    POSITIVE LOGITS
     Joined
    0.89
     whom
    0.86
     who
    0.81
     surn
    0.77
     nicknamed
    0.76
     whose
    0.75
     residing
    0.69
     wrestler
    0.68
     specializing
    0.68
     befriend
    0.67
    Activations Density 0.036%

    No Known Activations