© 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 EvalsExportsinterp-engineNEWAPI 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. 5480
    Prev
    Next
    INDEX
    Explanations

    passive voice constructions, especially with past participles

    oai_token-act-pair · gpt-3.5-turbo

    references to conditions and consequences related to illness or health risks

    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
    clus
    -0.72
    gins
    -0.68
    LD
    -0.68
    ername
    -0.65
    ience
    -0.63
    ccording
    -0.63
    Facebook
    -0.62
    lishes
    -0.62
     Politics
    -0.61
    spons
    -0.61
    POSITIVE LOGITS
     been
    0.86
    aru
    0.79
     be
    0.79
     being
    0.78
    inventoryQuantity
    0.78
    be
    0.75
    ãĥĵ
    0.74
    Be
    0.73
     Be
    0.72
    being
    0.71
    Activations Density 0.129%

    No Known Activations