© 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. 4675
    Prev
    Next
    INDEX
    Explanations

    the names of fantasy creatures and battle-related terms

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

    phrases or constructs related to statistics or numerical data

    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
    away
    -0.68
    BILL
    -0.68
     interviewed
    -0.67
    aday
    -0.67
    YA
    -0.66
     interfered
    -0.66
     briefed
    -0.65
     seriously
    -0.65
     afforded
    -0.64
    Website
    -0.63
    POSITIVE LOGITS
     Ages
    1.00
     Osiris
    0.95
     Souls
    0.94
     Destruction
    0.92
     Hera
    0.91
     Plenty
    0.91
     Despair
    0.90
     Wisdom
    0.90
     Salvation
    0.88
     Doom
    0.88
    Activations Density 0.126%

    No Known Activations