© 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. 13977
    Prev
    Next
    INDEX
    Explanations

    words related to medical procedures or conditions mentioned with a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "oc" in words

    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
     Uriel
    -0.73
    Known
    -0.65
    ĪĴ
    -0.65
     hope
    -0.63
    à¥
    -0.62
    ĸļ
    -0.61
     intention
    -0.61
     garment
    -0.59
     Ames
    -0.58
    words
    -0.58
    POSITIVE LOGITS
    entric
    1.42
    kefeller
    1.39
    abulary
    1.21
    arbon
    1.17
    hester
    1.15
    urrencies
    1.09
    ombat
    1.07
    onut
    1.06
    chio
    1.05
    razy
    1.04
    Activations Density 0.026%

    No Known Activations