© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    words related to physically demanding or challenging situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grueling."

    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
    ĺħ
    -0.71
     Carbuncle
    -0.68
    etheless
    -0.62
     attraction
    -0.62
    IU
    -0.59
     upside
    -0.57
     Slash
    -0.56
     basin
    -0.56
     Waterloo
    -0.56
    aneously
    -0.55
    POSITIVE LOGITS
    eling
    1.53
    ppo
    1.30
    esome
    1.28
    enhagen
    1.08
    ff
    1.05
    ppe
    1.04
    eled
    1.02
    atown
    0.99
    ffer
    0.98
    pp
    0.95
    Activations Density 0.053%

    No Known Activations