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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 768
    5. 8-RES_FS768-JB
    6. 157
    Prev
    Next
    INDEX
    Explanations

    information about fundraising campaigns and donations for various causes

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    488
    +0.12
    0.6%
    592
    +0.12
    0.5%
    407
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    488
    +0.12
    0.13
    592
    +0.12
    0.10
    13
    +0.11
    0.13
    Negative Logits
    Temperature
    -0.82
    spect
    -0.78
    Í
    -0.72
    ierre
    -0.72
    ife
    -0.68
    ovie
    -0.68
     Occupations
    -0.68
     tem
    -0.67
    uder
    -0.66
    amb
    -0.65
    POSITIVE LOGITS
     reimburse
    1.53
     payable
    1.44
     (£
    1.41
     dollars
    1.41
     payments
    1.40
     rebate
    1.39
     ($
    1.39
     reimb
    1.39
     reimbursement
    1.38
     coffers
    1.36
    Activations Density 5.306%

    No Known Activations