© 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. 23095
    Prev
    Next
    INDEX
    Explanations

    words related to materials or substances, particularly those containing "ure."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ure" and its variations in different contexts

    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
     aside
    -0.63
     carcin
    -0.57
     lax
    -0.57
     forward
    -0.56
    agher
    -0.56
     uniform
    -0.55
     induct
    -0.54
     succession
    -0.54
     odds
    -0.54
     mileage
    -0.54
    POSITIVE LOGITS
    Reloaded
    1.13
    gio
    1.10
    mberg
    1.03
    nces
    0.95
    lio
    0.92
    ka
    0.86
    mb
    0.83
    nc
    0.82
    lia
    0.82
    nce
    0.82
    Activations Density 0.159%

    No Known Activations