© 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. 11239
    Prev
    Next
    INDEX
    Explanations

    phrases related to affordability or cost

    oai_token-act-pair · gpt-3.5-turbo

    mentions of offers and availability for products or services

    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
    failed
    -0.78
    alky
    -0.74
    icism
    -0.74
    tsky
    -0.72
    intention
    -0.71
     Bernstein
    -0.70
    sis
    -0.70
    ipolar
    -0.68
    hei
    -0.67
    enment
    -0.67
    POSITIVE LOGITS
     handy
    1.31
     goodies
    1.27
     yours
    1.19
     discounts
    1.12
     nifty
    1.12
     specials
    1.11
     stocked
    1.06
     tasty
    1.04
     FREE
    1.04
     extras
    1.03
    Activations Density 0.900%

    No Known Activations