© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3512
    Prev
    Next
    INDEX
    Explanations

    information related to bacteria and bacterial cultures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    keywords related to bacterial infections and microbiology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dash
    -0.84
    onga
    -0.82
    nesota
    -0.80
    fman
    -0.78
    rl
    -0.74
    EStream
    -0.71
     largeDownload
    -0.71
    quished
    -0.68
    olphin
    -0.68
    rontal
    -0.68
    POSITIVE LOGITS
     infections
    1.19
     spores
    1.18
     infection
    1.12
     strains
    1.10
    icidal
    1.06
     pathogens
    1.04
     fermentation
    1.03
     flora
    1.01
     contamination
    1.00
     bacteria
    1.00
    Activations Density 0.063%

    No Known Activations