© 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. 3147
    Prev
    Next
    INDEX
    Explanations

    positive descriptions or traits related to individuals or groups

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

    expressions of personal experiences and social relationships

    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
    Paper
    -0.70
     Dumb
    -0.67
    HUD
    -0.67
     Decision
    -0.63
    major
    -0.62
    govtrack
    -0.62
    olicy
    -0.62
     Mayhem
    -0.62
    lip
    -0.61
    udget
    -0.61
    POSITIVE LOGITS
     exhibited
    1.10
     displayed
    1.01
     cultivated
    0.99
     eng
    0.99
     possess
    0.94
     fost
    0.91
     possessed
    0.90
     muster
    0.90
     bestowed
    0.90
     enjoyed
    0.89
    Activations Density 0.175%

    No Known Activations