© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5921
    Prev
    Next
    INDEX
    Explanations

    information on specific topics or entities indicated in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate seeking information or learning more about a topic

    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
    albeit
    -0.82
    cffffcc
    -0.82
    ©¶æ¥µ
    -0.75
    typically
    -0.73
    bably
    -0.72
     teasp
    -0.71
    oultry
    -0.69
    gered
    -0.68
    $$$$
    -0.67
    usercontent
    -0.66
    POSITIVE LOGITS
     why
    1.06
     how
    0.99
     our
    0.78
     this
    0.77
     whats
    0.73
     WHY
    0.73
     these
    0.70
    why
    0.69
     what
    0.68
     Yourself
    0.66
    Activations Density 0.093%

    No Known Activations