© 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. 9-RES-JB
    11. 18389
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of individuals with a prefix "Dr." person

    oai_token-act-pair · gpt-3.5-turbo

    references to doctors or medical professionals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thumbnails
    -0.73
     gearing
    -0.70
    mble
    -0.70
     defences
    -0.67
     ranger
    -0.65
     capitals
    -0.64
     capped
    -0.64
     redundancy
    -0.64
     settled
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     Jill
    1.07
     âĸĪ
    0.95
     Pepper
    0.94
     Canaver
    0.92
     Crusher
    0.91
     Opp
    0.89
     Robert
    0.89
     Lawrence
    0.87
    icio
    0.86
     William
    0.86
    Activations Density 0.044%

    No Known Activations