© 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. 13968
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial or impactful statements made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to public statements or comments

    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
    ccording
    -0.78
    bid
    -0.77
    PG
    -0.77
    tis
    -0.77
    wick
    -0.67
    Mech
    -0.64
     Craw
    -0.63
    tails
    -0.62
     erection
    -0.62
    tail
    -0.62
    POSITIVE LOGITS
     uttered
    1.15
     regarding
    1.11
     about
    1.07
     dispar
    1.04
     aloud
    1.00
     implying
    0.99
     remarks
    0.99
     concerning
    0.97
     criticizing
    0.94
     praising
    0.94
    Activations Density 0.087%

    No Known Activations