© 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. 20452
    Prev
    Next
    INDEX
    Explanations

    verbs related to skills or actions along with nouns related to work or tasks

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to learning and educational themes

    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
    but
    -0.76
     But
    -0.73
    But
    -0.70
     guiIcon
    -0.67
     à¨
    -0.64
     but
    -0.64
    ?,
    -0.64
     âĢ
    -0.64
    Except
    -0.63
    DragonMagazine
    -0.59
    POSITIVE LOGITS
     therein
    0.86
     utilizing
    0.83
     thereof
    0.83
     thereto
    0.78
     impacting
    0.73
     throughout
    0.73
     respectively
    0.67
     accordingly
    0.66
     athlet
    0.66
     leveraging
    0.65
    Activations Density 1.129%

    No Known Activations