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. 3799
    Prev
    Next
    INDEX
    Explanations

    collections or groups of items

    oai_token-act-pair · gpt-3.5-turbo

    references to collections of items or works

    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
    atism
    -0.77
    pher
    -0.75
    avin
    -0.70
    abilities
    -0.67
     Osw
    -0.65
    lan
    -0.64
    killed
    -0.64
    quit
    -0.63
    quickShipAvailable
    -0.63
    adv
    -0.63
    POSITIVE LOGITS
     collection
    3.77
     collections
    2.76
    collection
    2.75
     Collection
    2.75
    Collection
    2.16
     Collections
    1.85
     collecting
    1.78
     collectors
    1.76
     collector
    1.73
     collected
    1.61
    Activations Density 0.018%

    No Known Activations