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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12256
    Prev
    Next
    INDEX
    Explanations

    phrases related to drills or practice sessions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "drill" in various contexts related to training or simulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.73
    CHO
    -0.72
    HCR
    -0.68
    é¾įå
    -0.65
     Hope
    -0.65
     Hep
    -0.64
     Reincarn
    -0.62
    Examples
    -0.62
     Governments
    -0.62
     Leilan
    -0.62
    POSITIVE LOGITS
     drilled
    1.29
     drill
    1.23
     drilling
    1.08
     drills
    1.07
     sergeant
    1.02
    itud
    1.01
     Drill
    0.98
    arious
    0.82
     rigs
    0.79
     instructor
    0.79
    Activations Density 0.014%

    No Known Activations