© 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. 2484
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking advantage of situations or opportunities

    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
    679
    +0.14
    0.6%
    259
    +0.09
    0.4%
    285
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    259
    +0.14
    0.01
    369
    +0.09
    0.01
    271
    +0.09
    0.01
    Negative Logits
    jah
    -0.67
    don
    -0.65
    inguishable
    -0.65
     haz
    -0.64
    gru
    -0.64
     brace
    -0.64
    odd
    -0.61
    liam
    -0.60
     fireball
    -0.59
     manic
    -0.57
    POSITIVE LOGITS
     thereof
    0.90
    fully
    0.85
    ously
    0.82
    oise
    0.80
    FUL
    0.80
    ful
    0.74
     loopholes
    0.70
    nels
    0.69
    fulness
    0.68
    tesy
    0.67
    Activations Density 0.019%

    No Known Activations