© 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. 3-RES-JB
    11. 1560
    Prev
    Next
    INDEX
    Explanations

    references to the word "thumbs" being used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to approval or disapproval, often indicated by the term "thumbs" along with associated numerical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ople
    -0.85
    ioned
    -0.83
    iated
    -0.80
    rosso
    -0.77
     Lauder
    -0.76
    ional
    -0.75
    ively
    -0.75
    icut
    -0.74
    erie
    -0.73
    riad
    -0.73
    POSITIVE LOGITS
    umbs
    1.02
     thumbs
    0.98
    pace
    0.77
    Quantity
    0.74
    itzer
    0.73
    éĹĺ
    0.72
     Flavoring
    0.70
    addle
    0.70
    ickets
    0.67
    ission
    0.64
    Activations Density 0.019%

    No Known Activations