© 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 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. 3232
    Prev
    Next
    INDEX
    Explanations

    texts that include notes, signs, disclaimers, stickers, banners, or labels

    oai_token-act-pair · gpt-3.5-turbo

    references to notes, signs, and captions within the text

    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
     passions
    -0.77
    kus
    -0.77
     Cosponsors
    -0.77
    姫
    -0.77
    apeake
    -0.73
     Fellow
    -0.68
    iencies
    -0.68
    issance
    -0.66
    rates
    -0.66
    maxwell
    -0.66
    POSITIVE LOGITS
     stating
    1.39
     proclaiming
    1.33
     printed
    1.27
     informing
    1.23
     indicating
    1.23
     detailing
    1.22
     booklet
    1.21
     handwritten
    1.19
     thanking
    1.17
     advising
    1.17
    Activations Density 0.295%

    No Known Activations