© 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. 11374
    Prev
    Next
    INDEX
    Explanations

    mentions of medical procedures or body parts

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters that may indicate specific categories or classifications, particularly those related to medical terms or scientific concepts

    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
     newsp
    -0.70
     contribut
    -0.65
     ministerial
    -0.62
    oulos
    -0.61
     Debor
    -0.60
     elig
    -0.60
     reluct
    -0.60
     administ
    -0.60
     disadvant
    -0.60
     administrative
    -0.60
    POSITIVE LOGITS
    worm
    1.14
    worms
    1.07
    breaker
    1.03
    less
    1.01
    osate
    0.98
    pipe
    0.96
    hunter
    0.96
    heads
    0.95
    fish
    0.94
    paste
    0.93
    Activations Density 0.232%

    No Known Activations