© 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. 10-RES-JB
    11. 11140
    Prev
    Next
    INDEX
    Explanations

    the word 'Bad'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Badger" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.73
    thens
    -0.68
     corps
    -0.66
     helic
    -0.66
    conservancy
    -0.63
    izabeth
    -0.61
    accompan
    -0.61
     trough
    -0.57
     shelves
    -0.57
     alive
    -0.57
    POSITIVE LOGITS
    ger
    1.28
    ges
    1.20
    gers
    1.14
    ged
    1.11
    die
    1.04
    lands
    1.01
    dies
    1.00
    ge
    0.97
    ass
    0.96
    ging
    0.90
    Activations Density 0.013%

    No Known Activations