© 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. 20871
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing points or stating facts

    oai_token-act-pair · gpt-3.5-turbo

    statements starting with "The fact that."

    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
    Interested
    -0.63
    Refer
    -0.62
     Annotations
    -0.62
    nas
    -0.61
    cart
    -0.60
    begin
    -0.59
    ;;
    -0.58
     Caption
    -0.58
     Orig
    -0.54
    +.
    -0.54
    POSITIVE LOGITS
     remains
    0.97
    oid
    0.88
    uality
    0.85
     begs
    0.81
     is
    0.79
     proves
    0.77
    oids
    0.76
     that
    0.75
     indicates
    0.75
    itious
    0.73
    Activations Density 0.045%

    No Known Activations