© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11439
    Prev
    Next
    INDEX
    Explanations

    phrases related to online forms and requests

    oai_token-act-pair · gpt-3.5-turbo

    terms related to requests, forms, and processes associated with transactions or services

    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
     juven
    -0.75
    BuyableInstoreAndOnline
    -0.73
     Moe
    -0.66
     Compton
    -0.65
     Clancy
    -0.63
     ancest
    -0.62
     Parenthood
    -0.62
     Haram
    -0.61
     Inher
    -0.61
     inherit
    -0.60
    POSITIVE LOGITS
    able
    1.45
    ees
    1.22
    ables
    1.17
    ee
    1.13
    ability
    1.09
     button
    1.01
     request
    0.99
    bot
    0.97
     requests
    0.95
    button
    0.92
    Activations Density 0.337%

    No Known Activations