© 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. 372
    Prev
    Next
    INDEX
    Explanations

    phrases related to bears

    oai_token-act-pair · gpt-3.5-turbo

    references to bears and their various contexts and meanings

    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
     FISA
    -0.85
    Interstitial
    -0.82
    ijn
    -0.82
     Osc
    -0.81
    endez
    -0.79
     Wilkinson
    -0.78
     Mourinho
    -0.77
     Jess
    -0.76
     ESP
    -0.75
     Tele
    -0.75
    POSITIVE LOGITS
     bear
    2.31
     Bear
    2.21
     bears
    2.17
    Bear
    2.11
    bear
    2.03
     Bears
    1.88
     grizz
    1.72
     Grizz
    1.70
     cub
    1.33
     wolf
    1.22
    Activations Density 0.219%

    No Known Activations