© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 2248
    Prev
    Next
    INDEX
    Explanations

    references to media content such as images and videos

    oai_token-act-pair · gpt-3.5-turbo

    references to media sources and quotes from statements

    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
     turkey
    -0.88
    urd
    -0.88
     Ao
    -0.81
     Tro
    -0.81
    resy
    -0.80
     Romo
    -0.79
     carc
    -0.79
     Rath
    -0.77
     Spo
    -0.77
     Tyr
    -0.77
    POSITIVE LOGITS
     Mitchell
    2.07
    Mit
    1.78
     Daniel
    1.41
    Daniel
    1.27
     Luk
    1.18
     Benson
    1.17
    mit
    1.10
     Mitch
    1.07
    chell
    1.03
     Mit
    1.01
    Activations Density 0.405%

    No Known Activations