© 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. 1433
    Prev
    Next
    INDEX
    Explanations

    locations or place names

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence endings

    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
     ðŁĻĤ
    -0.56
     THEN
    -0.52
    Therefore
    -0.52
     THEY
    -0.50
     EVERY
    -0.50
     Presidents
    -0.49
     ourselves
    -0.49
     ONLY
    -0.49
     secondly
    -0.49
     BUT
    -0.48
    POSITIVE LOGITS
    CVE
    0.47
    posure
    0.47
    ielding
    0.46
    isoft
    0.46
    rift
    0.46
    dayName
    0.45
    rils
    0.45
    PLIED
    0.43
    held
    0.43
    utenberg
    0.42
    Activations Density 0.860%

    No Known Activations