© 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. 12-RES-JB
    11. 3902
    Prev
    Next
    INDEX
    Explanations

    references to the opening of locations, buildings, or facilities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to the opening or establishment of locations and facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ecd
    -0.76
    govtrack
    -0.73
    ĪĴ
    -0.73
    orge
    -0.72
    eric
    -0.71
     constitu
    -0.67
    ¿½
    -0.65
    oros
    -0.64
    errors
    -0.64
    é¾įå
    -0.64
    POSITIVE LOGITS
     doors
    1.01
     its
    0.95
     shop
    0.84
     downtown
    0.84
     Doors
    0.81
     nationwide
    0.79
     permanently
    0.77
     renovations
    0.77
     Sundays
    0.77
     up
    0.76
    Activations Density 0.099%

    No Known Activations