© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5029
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, places, and mentions of people or brands

    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
     Ree
    -0.85
    GRE
    -0.77
    ITNESS
    -0.77
    ugi
    -0.77
     Lansing
    -0.76
    Gil
    -0.76
    Joy
    -0.75
    uga
    -0.75
     Gree
    -0.74
    isSpecialOrderable
    -0.73
    POSITIVE LOGITS
     Ant
    2.35
    Ant
    2.19
     ant
    1.99
    ANT
    1.78
     ants
    1.76
    ant
    1.58
     Anton
    1.47
     Anthem
    1.23
    antis
    1.18
     antip
    1.18
    Activations Density 0.259%

    No Known Activations