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. 17482
    Prev
    Next
    INDEX
    Explanations

    keywords related to vineyards and wine production

    oai_token-act-pair · gpt-3.5-turbo

    references to vineyards and herds of animals

    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
    FH
    -0.80
     Crim
    -0.76
     menstru
    -0.74
     FRE
    -0.74
    hemat
    -0.73
     FM
    -0.72
    zai
    -0.72
     menstrual
    -0.70
     CF
    -0.70
    DCS
    -0.69
    POSITIVE LOGITS
     vine
    3.54
     vines
    2.59
     Vine
    2.21
    vine
    2.00
     herd
    1.89
     cellar
    1.48
     herds
    1.45
     flock
    1.39
     pasture
    1.33
     grapes
    1.30
    Activations Density 0.034%

    No Known Activations