© 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. 17198
    Prev
    Next
    INDEX
    Explanations

    technical information or forum posts, perhaps related to a specific topic or website

    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
    373
    +0.43
    2.8%
    481
    +0.38
    2.4%
    87
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.43
    -0.11
    87
    +0.38
    -0.07
    481
    +0.15
    0.15
    Negative Logits
    )."
    -0.52
    sic
    -0.51
    =]
    -0.49
    )</
    -0.49
     [âĢ¦]
    -0.48
    .""
    -0.47
    milo
    -0.46
    âĢ¦]
    -0.45
    .).
    -0.43
    !".
    -0.43
    POSITIVE LOGITS
     Canaver
    0.58
    ©¶æ
    0.56
    iannopoulos
    0.45
     Arpaio
    0.41
     HuffPost
    0.41
    etheless
    0.39
     Weiner
    0.39
     Fiorina
    0.39
    vernment
    0.39
     Lyons
    0.38
    Activations Density 3.382%

    No Known Activations