© 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. 13739
    Prev
    Next
    INDEX
    Explanations

    hands of a clock

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating numerical values or measurements

    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
    natureconservancy
    -0.53
     pains
    -0.49
     disclaimer
    -0.47
     thumbs
    -0.47
     jargon
    -0.47
     enh
    -0.45
     noises
    -0.45
     bluff
    -0.44
     minded
    -0.44
    ingen
    -0.44
    POSITIVE LOGITS
    ãĤ¹
    0.68
    boss
    0.54
    ubes
    0.51
    dinand
    0.51
    endi
    0.51
    *=-
    0.50
    onymous
    0.49
    retched
    0.48
    eta
    0.48
    å£
    0.47
    Activations Density 0.309%

    No Known Activations