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 1536
    5. 8-RES_FS1536-JB
    6. 662
    Prev
    Next
    INDEX
    Explanations

    financial and business terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    314
    +0.12
    0.5%
    679
    +0.11
    0.5%
    744
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.12
    0.07
    140
    +0.11
    0.07
    132
    +0.10
    0.05
    Negative Logits
     habitable
    -0.66
    ¯¯
    -0.64
    asse
    -0.63
    hetti
    -0.63
    inished
    -0.63
     Hamm
    -0.62
     sweat
    -0.58
     Stark
    -0.58
     solvent
    -0.58
    BuyableInstoreAndOnline
    -0.58
    POSITIVE LOGITS
    worthy
    1.12
    flash
    1.11
    feed
    1.10
    room
    1.10
    reader
    1.08
    groups
    1.03
    worthiness
    1.00
    day
    0.95
    rooms
    0.94
    letters
    0.92
    Activations Density 1.326%

    No Known Activations