© 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. 15953
    Prev
    Next
    INDEX
    Explanations

    references to specific legal acts along with their corresponding years of enactment

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legislative acts and their corresponding years

    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
    ngth
    -0.77
    ozyg
    -0.70
    want
    -0.69
    gow
    -0.67
    emonic
    -0.66
    anthrop
    -0.63
    hett
    -0.63
    uyomi
    -0.63
    optim
    -0.61
    DragonMagazine
    -0.59
    POSITIVE LOGITS
     1974
    1.12
     1973
    1.06
     1978
    1.05
     1958
    0.99
     1988
    0.99
     1975
    0.99
     1965
    0.99
     1968
    0.99
     1994
    0.99
     1948
    0.98
    Activations Density 0.060%

    No Known Activations