© 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
    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. 24185
    Prev
    Next
    INDEX
    Explanations

    phrases related to victories or winning in sports

    oai_token-act-pair · gpt-3.5-turbo

    terms related to winning in competitive contexts

    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
    enegger
    -0.76
     Lak
    -0.60
     Fires
    -0.60
     Dupl
    -0.59
    opian
    -0.58
     encyclopedia
    -0.56
     Wrong
    -0.55
     Suicide
    -0.55
     heirs
    -0.55
    selves
    -0.54
    POSITIVE LOGITS
    nings
    1.34
     streak
    1.21
    stre
    1.19
    throp
    1.11
    less
    1.03
     streaks
    0.97
    now
    0.97
    ery
    0.94
    iem
    0.92
     expectancy
    0.90
    Activations Density 0.037%

    No Known Activations