© 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 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. 15039
    Prev
    Next
    INDEX
    Explanations

    words related to a specific medicinal plant called Kratom, as well as phrases related to pain relief and personal testimony

    oai_token-act-pair · gpt-3.5-turbo

    tokens related to the letter 't'

    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
    er
    -0.73
    VERTISEMENT
    -0.71
    ONSORED
    -0.68
    ĪĴ
    -0.66
     precedent
    -0.61
     resil
    -0.59
    e
    -0.56
    o
    -0.55
     Typhoon
    -0.54
     Flavoring
    -0.54
    POSITIVE LOGITS
    ronics
    1.15
    itles
    1.14
    ribune
    1.12
    anium
    1.06
    ractor
    1.03
    ronic
    1.02
    urtle
    1.02
    ucket
    1.01
    astic
    1.01
    iary
    1.00
    Activations Density 0.059%

    No Known Activations