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. 10-RES-JB
    6. 23112
    Prev
    Next
    INDEX
    Explanations

    references to legal entities or legal actions related to Cook County

    oai_token-act-pair · gpt-3.5-turbo

    references to "Cook" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.94
    ilitary
    -0.65
     elig
    -0.61
    ulous
    -0.61
    venants
    -0.60
     Wem
    -0.60
    orporated
    -0.59
    dfx
    -0.59
     Manila
    -0.59
    orb
    -0.58
    POSITIVE LOGITS
    book
    1.27
    books
    1.26
    Cook
    1.00
    ery
    0.94
    cook
    0.92
    stall
    0.92
    ies
    0.91
    shop
    0.89
    batch
    0.88
    bread
    0.86
    Activations Density 0.030%

    No Known Activations