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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14163
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Fitts."

    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
    285
    +0.11
    0.5%
    582
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.02
    582
    +0.11
    0.01
    492
    +0.10
    0.01
    Negative Logits
     womb
    -0.72
    cles
    -0.70
    ©¶æ
    -0.65
    Copy
    -0.64
    ħĭ
    -0.62
     departure
    -0.61
     Xer
    -0.61
     Uzbek
    -0.60
    Ļ½
    -0.58
     veins
    -0.58
    POSITIVE LOGITS
    sburgh
    1.57
    orio
    0.99
    leness
    0.98
    erella
    0.98
    enger
    0.95
    les
    0.94
    erer
    0.93
    robe
    0.91
    ake
    0.89
    matter
    0.89
    Activations Density 0.023%

    No Known Activations