© 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. 9090
    Prev
    Next
    INDEX
    Explanations

    instances of a specific phrase, probably related to a specific event or action

    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
    702
    +0.12
    0.5%
    445
    +0.10
    0.4%
    35
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.12
    0.02
    431
    +0.10
    0.02
    259
    +0.10
    0.01
    Negative Logits
    ²
    -0.65
    ãĥ«
    -0.65
    ãĥ¼ãĥ
    -0.62
    ãĥĺ
    -0.59
     present
    -0.59
    é¾įå¥ij士
    -0.59
    968
    -0.58
    herent
    -0.58
    hips
    -0.58
    ãĤ±
    -0.58
    POSITIVE LOGITS
    !,
    0.95
    !.
    0.88
    chy
    0.86
    !
    0.81
    !'
    0.78
    alian
    0.76
    ÃĥÃĤ
    0.72
    chwitz
    0.69
    lla
    0.68
    self
    0.68
    Activations Density 0.064%

    No Known Activations