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. 10862
    Prev
    Next
    INDEX
    Explanations

    specific categories or groupings of items

    oai_token-act-pair · gpt-3.5-turbo

    mentions of categories or classifications

    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
    hire
    -0.73
    shock
    -0.69
    [/
    -0.68
    idge
    -0.66
    sei
    -0.66
    olt
    -0.66
    uber
    -0.65
    pire
    -0.65
    fort
    -0.63
     crest
    -0.62
    POSITIVE LOGITS
     categories
    3.62
     Categories
    2.24
     category
    2.14
     genres
    1.84
    Category
    1.61
    ategories
    1.61
     Category
    1.54
     tiers
    1.49
    category
    1.47
     formats
    1.47
    Activations Density 0.009%

    No Known Activations