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. 20104
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the pseudonym 'Satoshi'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Sat" and variations of "sat" in different contexts

    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
    naire
    -0.85
    enegger
    -0.78
    EStreamFrame
    -0.75
    pressed
    -0.70
    resent
    -0.70
    Ø©
    -0.68
    ãģª
    -0.68
    ãĤĭ
    -0.68
    女
    -0.67
    å¯
    -0.67
    POSITIVE LOGITS
    chel
    1.14
    chell
    1.12
    iva
    1.03
    ilda
    1.01
    rina
    1.00
    omi
    0.97
    alk
    0.96
    urn
    0.96
    gew
    0.95
    yrs
    0.95
    Activations Density 0.016%

    No Known Activations