© 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. 14675
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific types of physical items or structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to numerical quantities and counts in various contexts

    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
    ç·
    -0.77
    cgi
    -0.68
    edia
    -0.64
    inventoryQuantity
    -0.63
    00200000
    -0.63
    EngineDebug
    -0.62
    ãĥį
    -0.62
    cffffcc
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    thumbnails
    -0.58
    POSITIVE LOGITS
     apiece
    1.06
     consecut
    1.03
    mith
    1.03
     totaling
    1.01
    hips
    0.96
     plus
    0.87
     imaginable
    0.86
    poons
    0.84
    paces
    0.84
     vying
    0.84
    Activations Density 0.406%

    No Known Activations