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. 8-RES-JB
    6. 260
    Prev
    Next
    INDEX
    Explanations

    references to the human mouth or related topics like taste, sensing, speech, or dental health

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to the mouth and oral references

    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
     Myst
    -0.77
     Levi
    -0.69
     Avalon
    -0.64
     Scotia
    -0.64
     Syd
    -0.63
    irements
    -0.63
     Phi
    -0.62
     Wynne
    -0.62
     subp
    -0.61
     CES
    -0.60
    POSITIVE LOGITS
    piece
    1.46
    pieces
    1.28
    parts
    1.19
    wash
    1.12
    ful
    1.11
    ilage
    1.00
    bone
    0.98
    feel
    0.95
    poke
    0.94
    bones
    0.90
    Activations Density 0.037%

    No Known Activations