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. 23063
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "Sign Up"

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.10
    0.5%
    735
    +0.10
    0.4%
    398
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    735
    +0.10
    0.02
    398
    +0.10
    0.02
    586
    +0.09
    0.02
    Negative Logits
    mong
    -0.61
     serv
    -0.60
    ãĥīãĥ©ãĤ´ãĥ³
    -0.59
     dest
    -0.59
    cia
    -0.59
     repatri
    -0.57
    ially
    -0.55
     tal
    -0.55
     wast
    -0.55
     angel
    -0.54
    POSITIVE LOGITS
    ername
    0.78
     Thumbnails
    0.72
    grades
    0.71
     Continue
    0.71
     Picks
    0.69
    stairs
    0.66
    Norm
    0.64
     Submit
    0.63
     Emails
    0.63
    lish
    0.63
    Activations Density 0.012%

    No Known Activations