Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 522
    Prev
    Next
    INDEX
    Explanations

    services for repairing electronic devices and technology products, offering fast repair solutions and door-to-door collection and delivery

    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
    640
    +0.24
    1.1%
    679
    +0.12
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.24
    0.09
    640
    +0.12
    0.08
    679
    +0.10
    0.07
    Negative Logits
    umably
    -0.89
     pse
    -0.79
     gunfire
    -0.73
     presumably
    -0.73
     unlucky
    -0.71
    lier
    -0.71
     maiden
    -0.69
     metaph
    -0.69
     occupation
    -0.68
     unidentified
    -0.68
    POSITIVE LOGITS
     Includes
    1.40
     Featuring
    1.37
     Whether
    1.32
     Designed
    1.22
     Additionally
    1.19
     Each
    1.18
     Learn
    1.17
     Besides
    1.17
     Simply
    1.15
     Available
    1.14
    Activations Density 0.289%

    No Known Activations