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 49152
    5. 8-RES_FS49152-JB
    6. 26125
    Prev
    Next
    INDEX
    Explanations

    words related to style or materials, particularly in the context of fashion or design

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    555
    +0.12
    0.5%
    726
    +0.12
    0.5%
    70
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.12
    0.01
    70
    +0.12
    0.01
    726
    +0.12
    0.01
    Negative Logits
     WARN
    -0.76
    DERR
    -0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     circulation
    -0.63
     Participant
    -0.62
    ajor
    -0.62
     Mutual
    -0.62
    女
    -0.62
     THR
    -0.61
    agher
    -0.59
    POSITIVE LOGITS
    led
    1.21
    les
    1.12
    sty
    1.06
    gian
    1.06
    rette
    1.04
    lish
    1.03
    ling
    1.03
    rene
    1.00
    rian
    0.90
    rend
    0.87
    Activations Density 0.003%

    No Known Activations