© 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 EvalsExportsinterp-engineNEWAPI 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. 3354
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "field" in various contexts

    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
     Fas
    -0.72
     dism
    -0.68
     Seas
    -0.65
     Clause
    -0.63
    ILLE
    -0.62
    atron
    -0.61
     Claus
    -0.61
    ipop
    -0.60
    ibly
    -0.59
    Priv
    -0.59
    POSITIVE LOGITS
    sheet
    1.04
    work
    1.00
    workers
    0.93
    trip
    0.87
    grass
    0.85
     sob
    0.84
    finder
    0.83
    worker
    0.83
    smanship
    0.81
    quartered
    0.80
    Activations Density 0.038%

    No Known Activations