© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15959
    Prev
    Next
    INDEX
    Explanations

    academic references and citations in the format of a journal article

    oai_token-act-pair · gpt-3.5-turbo

    references to academic journals and articles

    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
    urally
    -0.81
    rower
    -0.75
    ertodd
    -0.65
    lessly
    -0.63
    leep
    -0.62
     judging
    -0.61
    ight
    -0.61
    esian
    -0.60
    reen
    -0.60
    ttle
    -0.59
    POSITIVE LOGITS
     doi
    1.13
     suppl
    1.08
     pg
    1.02
    doi
    1.00
     pp
    0.98
     Supplement
    0.97
     Issue
    0.96
    Issue
    0.93
     DOI
    0.93
     Supp
    0.88
    Activations Density 0.061%

    No Known Activations