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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4503
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "dedicate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pastebin
    -0.70
     Manip
    -0.67
     Surge
    -0.65
     Recession
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.62
     Terr
    -0.62
     Verge
    -0.62
     Train
    -0.61
     Weaver
    -0.60
    POSITIVE LOGITS
    ications
    1.29
     ded
    1.25
    uced
    1.21
    ication
    1.10
    icates
    1.07
    icated
    1.03
    icating
    1.03
    ucing
    0.99
    ifferent
    0.94
    iving
    0.93
    Activations Density 0.009%

    No Known Activations