© 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. 1323
    Prev
    Next
    INDEX
    Explanations

    names of cities or locations

    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
    421
    +0.14
    0.6%
    68
    +0.12
    0.5%
    380
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.02
    421
    +0.12
    0.01
    380
    +0.12
    0.01
    Negative Logits
    raid
    -0.72
     centrif
    -0.70
     dictate
    -0.69
    schild
    -0.67
     Ascend
    -0.66
    aeda
    -0.63
    hower
    -0.62
     flourish
    -0.60
     Gleaming
    -0.59
     Butterfly
    -0.59
    POSITIVE LOGITS
    eston
    1.34
    atan
    1.27
    ottesville
    1.15
    otte
    1.10
    ott
    0.97
    otine
    0.97
    otta
    0.96
    otten
    0.91
    iot
    0.87
    ues
    0.87
    Activations Density 0.022%

    No Known Activations