© 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. 17982
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations or entities along with associated monetary values

    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
    668
    +0.11
    0.5%
    516
    +0.11
    0.5%
    311
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    404
    +0.11
    0.03
    613
    +0.10
    0.03
    Negative Logits
    aro
    -0.81
    apo
    -0.81
    falls
    -0.74
    worms
    -0.74
    stones
    -0.72
    orem
    -0.72
    rises
    -0.71
    boxes
    -0.69
    erb
    -0.69
    ery
    -0.68
    POSITIVE LOGITS
    Ń·
    0.74
    GROUP
    0.74
    ÙĦ
    0.73
    --+
    0.70
    ãĤ¡
    0.69
    ħĭ
    0.69
    Õ
    0.69
    \":
    0.68
     sidx
    0.67
    WAYS
    0.67
    Activations Density 0.180%

    No Known Activations