© 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. 10-RES-JB
    11. 18989
    Prev
    Next
    INDEX
    Explanations

    phrases related to sales promotions and deals

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "for" related to various contexts and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.65
    Nevertheless
    -0.65
    /(
    -0.64
     advis
    -0.63
    ufficient
    -0.62
     thereof
    -0.62
    RFC
    -0.60
    ANN
    -0.60
    unal
    -0.59
    soever
    -0.59
    POSITIVE LOGITS
     sale
    1.29
     toddlers
    1.08
     kids
    1.05
     beginners
    1.04
    agers
    1.03
    ked
    0.95
     adults
    0.93
     Sale
    0.91
    bidden
    0.91
    aging
    0.90
    Activations Density 0.146%

    No Known Activations