© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4625
    Prev
    Next
    INDEX
    Explanations

    words or snippets starting with the letter "c" with an emphasis on particular spellings or patterns like "c9" or "c10"

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'c' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GOODMAN
    -0.86
    ãĥĹ
    -0.69
     Tinder
    -0.67
     Chero
    -0.63
    tenance
    -0.63
     Yamaha
    -0.63
     track
    -0.62
     Sacrament
    -0.61
     Dish
    -0.60
     Bain
    -0.59
    POSITIVE LOGITS
    rosso
    1.35
    ologne
    1.31
    rescent
    1.27
    auldron
    1.25
    elsius
    1.22
    aucas
    1.22
    ordon
    1.21
    heddar
    1.19
    actus
    1.19
    atered
    1.13
    Activations Density 0.030%

    No Known Activations