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. 1049
    Prev
    Next
    INDEX
    Explanations

    references to updates or changes in software applications

    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
    496
    +0.13
    0.6%
    7
    +0.10
    0.5%
    385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.13
    0.03
    201
    +0.10
    0.02
    696
    +0.10
    0.02
    Negative Logits
    ersive
    -0.79
    iage
    -0.74
    utical
    -0.68
     conclud
    -0.65
    doms
    -0.64
     artific
    -0.63
     includ
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
     haunt
    -0.59
    anni
    -0.59
    POSITIVE LOGITS
    SSL
    1.04
    Street
    0.93
    BSD
    0.92
    street
    0.87
    Indiana
    0.76
    Stack
    0.75
    office
    0.74
    VPN
    0.74
     Source
    0.73
    folio
    0.73
    Activations Density 0.024%

    No Known Activations