© 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. 11-RES-JB
    11. 3449
    Prev
    Next
    INDEX
    Explanations

    words related to the internet website "Ebay"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific online entity or brand, particularly associated with "eb" or similar variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ivities
    -0.78
     nomine
    -0.68
    hips
    -0.68
     Midnight
    -0.62
    ivity
    -0.58
     upstream
    -0.58
     commencement
    -0.58
     downstream
    -0.57
    ments
    -0.57
    cross
    -0.57
    POSITIVE LOGITS
    ruary
    1.44
    oard
    1.29
    urger
    1.15
    rahim
    1.13
    bies
    1.02
    edia
    1.01
    esity
    0.99
    uild
    0.97
    uilding
    0.95
    anon
    0.95
    Activations Density 0.051%

    No Known Activations