© 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. 2944
    Prev
    Next
    INDEX
    Explanations

    sentences conveying lack of understanding or the desire to hold people accountable

    oai_token-act-pair · gpt-3.5-turbo

    sentences or punctuation marks indicating the end of statements, particularly those that are marked with a period

    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
     challeng
    -0.86
     withd
    -0.80
     immersion
    -0.76
     inqu
    -0.75
     manif
    -0.74
     nodd
    -0.74
     dimensional
    -0.74
     dispos
    -0.70
     nuts
    -0.70
     glim
    -0.70
    POSITIVE LOGITS
     Photograph
    1.41
     Photo
    1.30
     Retrieved
    1.29
    jpg
    1.28
     REUTERS
    1.20
     Courtesy
    1.15
     Image
    1.12
     Provided
    1.09
     Accessed
    1.09
     PHOTO
    1.07
    Activations Density 0.220%

    No Known Activations