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. 4-RES-JB
    6. 7704
    Prev
    Next
    INDEX
    Explanations

    the word "thumbs" or related terms like "thumbs up" or "thumbs down"

    oai_token-act-pair · gpt-3.5-turbo

    references to approval or disapproval, particularly through the expression of "thumbs" actions

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

    No Comments

    Negative Logits
    lain
    -0.86
     Lauder
    -0.85
    ioned
    -0.79
    nets
    -0.74
     Cox
    -0.70
    abella
    -0.68
    anz
    -0.67
    inian
    -0.67
    lé
    -0.67
    anas
    -0.66
    POSITIVE LOGITS
    ++++
    0.95
    umbs
    0.82
    âĺħâĺħ
    0.81
     thumbs
    0.80
    urger
    0.78
    Quantity
    0.77
    xual
    0.75
    pe
    0.74
    peed
    0.73
    veyard
    0.70
    Activations Density 0.042%

    No Known Activations