© 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 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. 10171
    Prev
    Next
    INDEX
    Explanations

    the concept of lacking knowledge or understanding

    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
    722
    +0.09
    0.4%
    235
    +0.09
    0.4%
    354
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.09
    0.01
    722
    +0.09
    0.01
    505
    +0.09
    0.01
    Negative Logits
    ouri
    -0.69
    inka
    -0.67
    conn
    -0.65
    visor
    -0.64
    inos
    -0.63
    iki
    -0.61
    vertisement
    -0.61
    Pers
    -0.60
    istant
    -0.57
    byter
    -0.57
    POSITIVE LOGITS
     whatsoever
    1.05
     how
    1.03
     why
    0.99
     whats
    0.86
     whence
    0.86
     WHY
    0.84
    why
    0.84
     what
    0.83
    ledged
    0.83
     HOW
    0.81
    Activations Density 0.023%

    No Known Activations