© 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. 17456
    Prev
    Next
    INDEX
    Explanations

    descriptions of accidents or events

    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
    763
    +0.09
    0.4%
    674
    +0.09
    0.4%
    198
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.09
    0.06
    84
    +0.09
    0.03
    546
    +0.08
    0.04
    Negative Logits
    ħĭ
    -0.72
    aido
    -0.71
    rahim
    -0.68
    OND
    -0.68
    MI
    -0.64
    peria
    -0.63
    anners
    -0.62
    CHAT
    -0.62
    seeing
    -0.61
    NP
    -0.59
    POSITIVE LOGITS
     corro
    1.01
     dissip
    0.94
     exploded
    0.93
     resembles
    0.93
     mysteriously
    0.92
     resembled
    0.92
     contains
    0.91
     morphed
    0.90
     disinteg
    0.89
     disappears
    0.88
    Activations Density 0.450%

    No Known Activations