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. 0-RES-JB
    6. 5768
    Prev
    Next
    INDEX
    Explanations

    phrases related to abbreviations or proper nouns like "PCLOB" or "OB" followed by a numerical value, potentially indicating significance or priority

    oai_token-act-pair · gpt-3.5-turbo

    references to the abbreviation "OB" related to oversight or governance bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     covers
    -0.64
     enough
    -0.62
     Hung
    -0.61
     charging
    -0.61
     dance
    -0.60
     dancing
    -0.60
     sums
    -0.59
     meals
    -0.59
     mustard
    -0.59
    holders
    -0.59
    POSITIVE LOGITS
    OB
    4.32
     OB
    1.60
    ob
    1.55
    obs
    1.41
    OG
    1.40
    OP
    1.34
    obe
    1.33
    OPS
    1.32
    OF
    1.31
    OA
    1.29
    Activations Density 0.013%

    No Known Activations