© 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. 5667
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or entities, particularly related to news or events

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "For."

    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
     jaws
    -0.60
     antit
    -0.59
     coincides
    -0.57
     fraught
    -0.56
     linem
    -0.56
     vom
    -0.56
     conspic
    -0.53
     tailor
    -0.52
    mare
    -0.52
     Slug
    -0.52
    POSITIVE LOGITS
    bidden
    1.39
    gettable
    1.37
    gotten
    1.32
    gery
    1.26
    geries
    1.25
    given
    1.18
    cible
    1.17
    ged
    1.13
    wards
    1.12
    got
    1.12
    Activations Density 0.075%

    No Known Activations