© 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. 7-RES-JB
    11. 3148
    Prev
    Next
    INDEX
    Explanations

    mentions of ducks, including related terms such as "duckling" and "Duck Hunt."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the word "duck."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Palestin
    -0.74
     occas
    -0.70
     conclud
    -0.70
     millenn
    -0.66
     exercised
    -0.65
     agre
    -0.63
     alienated
    -0.63
     tangible
    -0.63
    Interstitial
    -0.62
    ×ij
    -0.62
    POSITIVE LOGITS
    lings
    1.21
    tails
    1.01
    weed
    1.00
     ducks
    0.93
    abee
    0.91
     duck
    0.89
     Goose
    0.88
    aroo
    0.86
    backs
    0.86
    bill
    0.86
    Activations Density 0.023%

    No Known Activations