© 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. 6161
    Prev
    Next
    INDEX
    Explanations

    words related to a specific location or place

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" and "A."

    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
     backgrounds
    -0.77
     APIs
    -0.76
     Labs
    -0.75
    Apps
    -0.75
    oids
    -0.73
     labs
    -0.73
     adrenaline
    -0.73
     outlets
    -0.72
     Emails
    -0.72
    NPR
    -0.71
    POSITIVE LOGITS
    ught
    1.14
     pious
    1.04
    rouse
    1.00
     thousand
    0.97
     magnificent
    0.96
     splendid
    0.94
    merce
    0.93
     servant
    0.93
     peasant
    0.93
     quarrel
    0.93
    Activations Density 0.251%

    No Known Activations