© 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. 11-RES-JB
    11. 20680
    Prev
    Next
    INDEX
    Explanations

    terminology related to organizational symbols and descriptions of authoritative actions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social discrimination and oppression

    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
    luaj
    -0.88
    BuyableInstoreAndOnline
    -0.72
    çīĪ
    -0.67
    BUG
    -0.66
    ?!"
    -0.65
    !'"
    -0.65
    TPP
    -0.63
    pictured
    -0.62
    !"
    -0.61
    udeb
    -0.61
    POSITIVE LOGITS
     or
    1.09
     predetermined
    0.90
     ordinarily
    0.88
     oneself
    0.87
     temporarily
    0.87
     irrespective
    0.86
     uncond
    0.83
     either
    0.81
     independently
    0.80
     characteristic
    0.80
    Activations Density 0.673%

    No Known Activations