© 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. 5208
    Prev
    Next
    INDEX
    Explanations

    dates in the format Month Year

    oai_token-act-pair · gpt-3.5-turbo
    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
     pu
    -0.93
     bananas
    -0.83
     banana
    -0.83
    pora
    -0.81
     squash
    -0.79
    Ub
    -0.77
     Banana
    -0.77
     Nero
    -0.77
    nc
    -0.77
     mashed
    -0.75
    POSITIVE LOGITS
     Hart
    2.17
     Hel
    2.14
    Hart
    1.99
    Hel
    1.85
     HEL
    1.83
     hel
    1.52
    hel
    1.47
     Helen
    1.38
     Helm
    1.31
     Hem
    1.27
    Activations Density 0.222%

    No Known Activations