© 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. 10522
    Prev
    Next
    INDEX
    Explanations

    references to specific people or positions within an organization

    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
    493
    +0.14
    0.6%
    758
    +0.09
    0.4%
    61
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.07
    493
    +0.09
    0.05
    547
    +0.09
    0.04
    Negative Logits
    ModLoader
    -0.79
    ÙĴ
    -0.68
    particip
    -0.64
    NetMessage
    -0.63
    ochond
    -0.63
    ÃįÃį
    -0.62
    theless
    -0.61
    ircraft
    -0.61
    isp
    -0.61
    ãĥĹ
    -0.61
    POSITIVE LOGITS
     Replay
    1.21
     |
    1.03
    >]
    0.88
     Read
    0.87
    ?'
    0.87
     Belfast
    0.85
     pic
    0.85
     */
    0.84
     Copyright
    0.83
     ];
    0.82
    Activations Density 0.566%

    No Known Activations