© 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. 10-RES-JB
    11. 11451
    Prev
    Next
    INDEX
    Explanations

    the term "Ill" or "Illinois" accompanied by various contexts and phrases

    oai_token-act-pair · gpt-3.5-turbo

    the word "Ill" and its context in medical or health-related discussions

    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
    SHIP
    -0.74
    \\\\\\\\\\\\\\\\
    -0.69
    =-=-=-=-=-=-=-=-
    -0.66
     elig
    -0.65
     compr
    -0.64
    ©¶æ¥µ
    -0.63
     Covenant
    -0.63
    #$#$
    -0.62
    è¦ļéĨĴ
    -0.62
     TABLE
    -0.61
    POSITIVE LOGITS
    ustration
    1.73
    uminati
    1.71
    inois
    1.63
    ust
    1.50
    usions
    1.48
    umin
    1.44
    usion
    1.30
    icit
    1.22
    ibrary
    1.16
    awar
    1.15
    Activations Density 0.015%

    No Known Activations