© 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. 11-RES-JB
    11. 14856
    Prev
    Next
    INDEX
    Explanations

    mentions of the substance "Kratom" and its effects on pain relief

    oai_token-act-pair · gpt-3.5-turbo

    empty segments or omissions in text

    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
     Azerb
    -0.04
    oÄŁ
    -0.03
    elsius
    -0.03
    ij士
    -0.03
     guiActiveUn
    -0.03
    Þ
    -0.03
     Vaugh
    -0.03
     pregn
    -0.03
    £ı
    -0.03
     miscar
    -0.03
    POSITIVE LOGITS
    ↵
    0.05
    The
    0.05
    -
    0.04
    A
    0.04
    In
    0.04
    .
    0.04
    ,
    0.04
     the
    0.04
    I
    0.04
    B
    0.04
    Activations Density 3.332%

    No Known Activations