© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10330
    Prev
    Next
    INDEX
    Explanations

    photo captions or credits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    373
    +0.13
    0.6%
    80
    +0.10
    0.4%
    710
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.13
    -0.00
    268
    +0.10
    0.02
    387
    +0.10
    0.03
    Negative Logits
    ModLoader
    -0.83
    cffff
    -0.81
    uchs
    -0.76
    iazep
    -0.71
    urnal
    -0.70
    imore
    -0.69
    anmar
    -0.66
    ority
    -0.66
    rador
    -0.66
    adian
    -0.65
    POSITIVE LOGITS
    journal
    0.72
    electric
    0.66
    >>>>>>>>
    0.63
     Niet
    0.61
    ################################
    0.61
    gdala
    0.61
     toggle
    0.60
     gallery
    0.60
    Shop
    0.60
     Finish
    0.59
    Activations Density 0.041%

    No Known Activations