© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    products or items that are described as high-quality, durable, or long-lasting in their respective contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future actions or results

    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
    quished
    -0.73
     Bernstein
    -0.71
    ween
    -0.63
     Faces
    -0.63
    announced
    -0.62
    raised
    -0.62
    Streamer
    -0.61
    reports
    -0.61
    animous
    -0.60
    annis
    -0.59
    POSITIVE LOGITS
     satisfy
    1.10
     suffice
    1.05
     help
    0.95
     fit
    0.95
     definitely
    0.94
     maximize
    0.92
     withstand
    0.91
     suit
    0.91
     enhance
    0.91
     impress
    0.90
    Activations Density 0.162%

    No Known Activations