© 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. 15022
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and computer programming

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names related to entities or organizations

    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
     eleph
    -0.99
    anwhile
    -0.93
     pione
    -0.91
    Þ
    -0.90
     conclud
    -0.85
     referen
    -0.83
    Ý
    -0.82
    ß
    -0.78
     teasp
    -0.77
    ñ
    -0.77
    POSITIVE LOGITS
    astery
    0.91
    usters
    0.87
    istries
    0.86
    omaly
    0.85
    etry
    0.82
    ioxide
    0.81
    itaire
    0.80
    rage
    0.79
    stice
    0.79
    ribune
    0.77
    Activations Density 0.143%

    No Known Activations