© 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. 1256
    Prev
    Next
    INDEX
    Explanations

    phrases indicating composition or a collection of items

    oai_token-act-pair · gpt-3.5-turbo

    words related to composition or structure

    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
    vision
    -0.58
    hello
    -0.57
    abad
    -0.57
    hawks
    -0.54
    Leaks
    -0.54
    Lear
    -0.53
    mort
    -0.52
    adesh
    -0.51
    justice
    -0.50
     Hazard
    -0.49
    POSITIVE LOGITS
     mainly
    1.14
     entirely
    1.14
     primarily
    1.13
     of
    1.08
     principally
    1.08
     chiefly
    1.07
     mostly
    1.07
     predominantly
    1.04
     solely
    1.03
     largely
    1.01
    Activations Density 0.061%

    No Known Activations