© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18702
    Prev
    Next
    INDEX
    Explanations

    phrases related to change and challenging situations

    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
    65
    +0.11
    0.5%
    563
    +0.11
    0.5%
    485
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.11
    0.04
    229
    +0.11
    0.03
    80
    +0.10
    0.03
    Negative Logits
    eva
    -0.85
    ".
    -0.82
    ";
    -0.78
    $.
    -0.75
     ".
    -0.75
     ();
    -0.75
    +.
    -0.71
     ."
    -0.71
    "!
    -0.70
    !".
    -0.68
    POSITIVE LOGITS
    ensibly
    0.66
     inaction
    0.63
    ItemThumbnailImage
    0.61
     Form
    0.60
    esides
    0.55
    actionDate
    0.53
     longest
    0.53
     hitherto
    0.53
     mediated
    0.52
     Weinstein
    0.52
    Activations Density 0.349%

    No Known Activations