© 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. 6-RES-JB
    11. 13625
    Prev
    Next
    INDEX
    Explanations

    terms related to names starting with "Ts" and "Sh" and prevalent in medical contexts

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns and names, particularly those related to individuals and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steen
    -0.68
     Eleanor
    -0.67
     Wonderland
    -0.66
    enegger
    -0.65
     Decay
    -0.65
    SourceFile
    -0.64
     Booker
    -0.62
     Ashes
    -0.62
     Dying
    -0.61
     suff
    -0.59
    POSITIVE LOGITS
    oslav
    0.98
    hett
    0.85
    士
    0.83
    raper
    0.82
    orah
    0.81
    illa
    0.78
    udos
    0.74
    arios
    0.74
    vous
    0.73
    letal
    0.73
    Activations Density 0.126%

    No Known Activations