© 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. 18872
    Prev
    Next
    INDEX
    Explanations

    promotions, deals, and offers

    oai_token-act-pair · gpt-3.5-turbo

    offers and promotions related to products and memberships

    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
    roman
    -0.71
     Grimm
    -0.68
     reconstruction
    -0.67
     displacement
    -0.67
     makeshift
    -0.67
     dwarves
    -0.66
     conject
    -0.66
    Occup
    -0.66
     improvised
    -0.65
     dissect
    -0.65
    POSITIVE LOGITS
     discounts
    1.72
     coupon
    1.70
     Discount
    1.56
     coupons
    1.55
     discount
    1.54
     discounted
    1.45
     rebate
    1.39
     pricing
    1.36
     unlimited
    1.35
     Coup
    1.34
    Activations Density 0.549%

    No Known Activations