© 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. 7-RES-JB
    11. 22952
    Prev
    Next
    INDEX
    Explanations

    streets or locations

    oai_token-act-pair · gpt-3.5-turbo

    specific locations, organizations, or notable titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ################################
    -0.61
     »
    -0.60
    Synopsis
    -0.54
    =-=-=-=-=-=-=-=-
    -0.54
    ————————
    -0.54
    ****************
    -0.54
     GOODMAN
    -0.54
     âľ
    -0.53
    Ô
    -0.52
     ðŁij
    -0.51
    POSITIVE LOGITS
    ).[
    0.78
    itime
    0.65
    oslav
    0.64
    foundland
    0.63
    miah
    0.63
    azel
    0.62
     Deng
    0.62
    intosh
    0.61
    )."
    0.60
    Lua
    0.59
    Activations Density 0.583%

    No Known Activations