© 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 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. 8-RES-JB
    11. 3433
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "flu"

    oai_token-act-pair · gpt-3.5-turbo

    references to influenza and related illnesses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Skydragon
    -0.85
     Fathers
    -0.81
     Limits
    -0.71
     guiActiveUnfocused
    -0.68
     Pwr
    -0.66
     Outer
    -0.65
     Parties
    -0.64
     Universe
    -0.63
     Cosmos
    -0.63
     Corpse
    -0.63
    POSITIVE LOGITS
    orescence
    1.46
    oresc
    1.39
    ency
    1.20
    enza
    1.15
    uates
    1.11
    iencies
    1.11
    ently
    1.07
    ipeg
    1.06
    encies
    1.06
    orescent
    1.02
    Activations Density 0.029%

    No Known Activations