© 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. 11530
    Prev
    Next
    INDEX
    Explanations

    terms related to medical specialists

    oai_token-act-pair · gpt-3.5-turbo

    references to financial figures and health-related terms

    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
    Synopsis
    -0.95
    ãĤ´ãĥ³
    -0.76
     triumph
    -0.74
     Suff
    -0.72
     triumphant
    -0.70
     rhetorical
    -0.68
     Released
    -0.66
     newfound
    -0.66
     resurg
    -0.66
     unworthy
    -0.65
    POSITIVE LOGITS
     somebody
    0.96
    entimes
    0.96
     [
    0.93
    ),"
    0.85
     anybody
    0.84
    )."
    0.84
     ambul
    0.83
     rentals
    0.83
     crews
    0.82
     ['
    0.82
    Activations Density 0.849%

    No Known Activations