© 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. 9-RES-JB
    11. 11186
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific country or organization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the acronym "SA" associated with 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
    ships
    -0.77
    ysis
    -0.71
    naires
    -0.66
    tons
    -0.65
    naire
    -0.65
     MacArthur
    -0.64
    hang
    -0.63
    estine
    -0.61
    ship
    -0.60
     ubiqu
    -0.60
    POSITIVE LOGITS
    VE
    1.12
    ven
    1.02
    plings
    0.95
    vant
    0.92
    ULT
    0.91
    ccess
    0.90
    pling
    0.89
    GE
    0.88
    FE
    0.86
    BILITIES
    0.84
    Activations Density 0.067%

    No Known Activations