© 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. 5012
    Prev
    Next
    INDEX
    Explanations

    references to updates or new information in various contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    terms related to updates and modifications

    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
    inki
    -0.74
    NetMessage
    -0.73
    zees
    -0.71
    ulhu
    -0.68
    WOOD
    -0.68
    PLIED
    -0.67
    baum
    -0.67
    ilyn
    -0.65
    dding
    -0.64
    hov
    -0.63
    POSITIVE LOGITS
     wording
    0.79
     rosters
    0.76
     menus
    0.75
     existing
    0.74
     constitution
    0.73
     reservation
    0.73
     fronts
    0.71
     timeline
    0.71
     menu
    0.71
     layout
    0.70
    Activations Density 0.264%

    No Known Activations