© 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. 11-RES-JB
    11. 15017
    Prev
    Next
    INDEX
    Explanations

    testimonials or endorsements of a product or remedy helping with pain

    oai_token-act-pair · gpt-3.5-turbo

    sentences or phrases that end with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ignition
    -0.71
    entimes
    -0.69
    alysed
    -0.67
     immedi
    -0.66
    etheless
    -0.65
     abduct
    -0.65
     downtime
    -0.64
    wcs
    -0.64
    ixty
    -0.64
     charact
    -0.64
    POSITIVE LOGITS
     Goodman
    1.05
     Browne
    1.04
     Bernstein
    1.02
     Lieberman
    1.01
     Stephens
    1.00
     Ware
    1.00
     Painter
    1.00
     Schiff
    0.99
     Stern
    0.99
     McDonnell
    0.99
    Activations Density 0.037%

    No Known Activations