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. 11-RES-JB
    6. 8684
    Prev
    Next
    INDEX
    Explanations

    mentions of Gothic architecture

    oai_token-act-pair · gpt-3.5-turbo

    references to notable Gothic architecture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MLG
    -1.00
     GSL
    -0.97
     Mississ
    -0.94
     Tulsa
    -0.93
     Oklahoma
    -0.92
     Durant
    -0.84
     Gork
    -0.84
     Maced
    -0.81
     Meridian
    -0.80
     IU
    -0.80
    POSITIVE LOGITS
     cats
    2.55
     Cats
    2.41
     cat
    2.39
     Cat
    2.21
     kittens
    2.11
    Cat
    2.09
     kitten
    1.99
    cats
    1.96
    cat
    1.84
     CAT
    1.58
    Activations Density 0.239%

    No Known Activations