© 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. 3338
    Prev
    Next
    INDEX
    Explanations

    names and titles related to local government officials

    oai_token-act-pair · gpt-3.5-turbo

    mentions of city council and related governance terms

    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
     Patriot
    -0.72
     Wasteland
    -0.71
     State
    -0.62
    antly
    -0.62
     helicopter
    -0.61
     Corinth
    -0.58
     Ducks
    -0.57
    !/
    -0.57
     Lithuan
    -0.57
     Marse
    -0.57
    POSITIVE LOGITS
    cill
    1.85
    selling
    1.30
    sell
    1.20
    cil
    1.18
    sels
    1.18
    plin
    1.17
    sel
    1.08
    perty
    0.97
    norm
    0.93
    llor
    0.91
    Activations Density 0.062%

    No Known Activations