© 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. 6102
    Prev
    Next
    INDEX
    Explanations

    company names and rankings

    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
    694
    +0.11
    0.5%
    649
    +0.10
    0.4%
    238
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.11
    0.04
    530
    +0.10
    0.04
    316
    +0.09
    0.04
    Negative Logits
     tremend
    -0.65
    ccording
    -0.58
    ij士
    -0.57
    ãĤ¼ãĤ¦ãĤ¹
    -0.56
    Ô
    -0.54
    senal
    -0.51
    âķIJâķIJ
    -0.51
     reconc
    -0.50
    é¾įåĸļ士
    -0.49
    76561
    -0.49
    POSITIVE LOGITS
    ↵
    1.74
    <|endoftext|>
    1.29
    ↵↵
    1.17
    SPONSORED
    0.98
    ;}
    0.76
     TBA
    0.74
    [/
    0.70
    ;
    0.68
    ↵Âł
    0.64
     /
    0.61
    Activations Density 0.234%

    No Known Activations