© 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. 9-RES-JB
    11. 14023
    Prev
    Next
    INDEX
    Explanations

    representations of the word "ignorance" or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "nig" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Franch
    -0.67
     Sparkle
    -0.63
     Emin
    -0.60
     Sussex
    -0.60
    Ĥª
    -0.57
    ãĥ¢
    -0.57
     CSI
    -0.57
     Leilan
    -0.56
    housing
    -0.56
    ÄŁ
    -0.56
    POSITIVE LOGITS
    arette
    1.28
    gers
    1.26
    rams
    1.18
    arettes
    1.18
    glers
    1.18
    gered
    1.14
    lia
    1.11
    abyte
    1.10
    roups
    1.09
    raphic
    1.08
    Activations Density 0.060%

    No Known Activations