© 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. 13974
    Prev
    Next
    INDEX
    Explanations

    references to catastrophic events or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cat" 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
    hower
    -0.74
    FontSize
    -0.69
    mble
    -0.69
    ij士
    -0.68
    OND
    -0.68
     Seym
    -0.66
    assetsadobe
    -0.66
     Institution
    -0.62
     Sacrament
    -0.62
    CRIP
    -0.62
    POSITIVE LOGITS
    aclysm
    1.60
    heter
    1.38
    apult
    1.28
    chers
    1.21
    hedral
    1.17
    alogue
    1.15
    cher
    1.14
    alyst
    1.08
    alog
    1.06
    fish
    1.06
    Activations Density 0.039%

    No Known Activations