© 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. 6722
    Prev
    Next
    INDEX
    Explanations

    coding errors and references in code snippets

    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
    +0.12
    0.6%
    380
    +0.11
    0.5%
    496
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.05
    373
    +0.11
    -0.02
    244
    +0.10
    0.03
    Negative Logits
    è¦ļéĨĴ
    -0.66
    obin
    -0.57
    ochet
    -0.57
    BI
    -0.55
     eleph
    -0.53
     bunk
    -0.53
    sections
    -0.52
    wire
    -0.52
    phen
    -0.52
    arch
    -0.52
    POSITIVE LOGITS
    Merit
    0.75
     WATCHED
    0.63
    ãħĭ
    0.63
    âĶĢâĶĢâĶĢâĶĢ
    0.61
    ãĥ»
    0.61
    Õ
    0.58
     Jr
    0.55
     eq
    0.55
    ̶
    0.54
    usted
    0.53
    Activations Density 0.199%

    No Known Activations