© 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. 10-RES-JB
    11. 5824
    Prev
    Next
    INDEX
    Explanations

    words related to medicine or medical conditions, specifically focusing on conditions or remedies that involve "ub" within them

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "ub" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Atlantic
    -0.73
     ORIG
    -0.71
     Clash
    -0.67
     Lauder
    -0.65
     drift
    -0.63
    ashtra
    -0.62
     ozone
    -0.62
    alez
    -0.61
     Nort
    -0.60
     Virgin
    -0.60
    POSITIVE LOGITS
    lishing
    1.35
    rious
    1.28
    bing
    1.27
    bles
    1.23
    lique
    1.20
    ilant
    1.20
    lish
    1.18
    bish
    1.16
    bed
    1.15
    ilee
    1.15
    Activations Density 0.027%

    No Known Activations