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 3072
    5. 8-RES_FS3072-JB
    6. 1116
    Prev
    Next
    INDEX
    Explanations

    information related to product giveaways and contests

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    592
    +0.13
    0.6%
    366
    +0.09
    0.4%
    515
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.13
    0.08
    248
    +0.09
    0.05
    500
    +0.09
    0.07
    Negative Logits
    inventoryQuantity
    -0.84
     metaphors
    -0.77
    ghazi
    -0.76
     ubiquitous
    -0.73
     clich
    -0.71
     sluggish
    -0.71
     generational
    -0.70
    baugh
    -0.70
    zbollah
    -0.69
     turbulence
    -0.68
    POSITIVE LOGITS
     PayPal
    1.23
     Reward
    1.18
     prizes
    1.11
     Sponsor
    1.10
     Participant
    1.10
     coupon
    1.08
    Registration
    1.08
     Rewards
    1.08
     refunds
    1.07
     Prize
    1.07
    Activations Density 2.722%

    No Known Activations