© 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 EvalsExportsAPI 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. 7469
    Prev
    Next
    INDEX
    Explanations

    mentions of or references to specific roles played by actors

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe actors and their roles in various productions

    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
     VIDEOS
    -0.90
    akings
    -0.86
    \.
    -0.81
    votes
    -0.80
    Frames
    -0.79
    wcs
    -0.77
    Notice
    -0.76
    Statistics
    -0.76
    zens
    -0.75
    RELATED
    -0.75
    POSITIVE LOGITS
     Agent
    1.06
     Colonel
    1.03
     Detective
    1.03
     narrator
    1.00
     Inspector
    0.99
     Captain
    0.99
     Sheriff
    0.96
     Peggy
    0.92
     Gand
    0.92
     Lois
    0.92
    Activations Density 0.116%

    No Known Activations