© 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. 6-RES-JB
    11. 9523
    Prev
    Next
    INDEX
    Explanations

    locations or places, specifically plazas

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.88
    nesses
    -0.76
    bone
    -0.75
     marrow
    -0.75
    body
    -0.73
    loss
    -0.72
     groom
    -0.72
    rack
    -0.72
    rolled
    -0.71
    angler
    -0.71
    POSITIVE LOGITS
     Mons
    0.86
    BILITY
    0.85
    pty
    0.82
    pport
    0.79
    aic
    0.78
    iries
    0.77
    BILITIES
    0.76
    hiba
    0.76
    uthor
    0.76
    ãĥ´ãĤ¡
    0.75
    Activations Density 0.059%

    No Known Activations