© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10623
    Prev
    Next
    INDEX
    Explanations

    statements of strong opinions or threats

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal issues and moral dilemmas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odder
    -0.68
     Scholar
    -0.63
     Horizons
    -0.62
     Sail
    -0.61
     Merchants
    -0.60
     Seller
    -0.59
    aughters
    -0.58
    merce
    -0.58
     Worlds
    -0.57
     Moons
    -0.57
    POSITIVE LOGITS
    ãĥ»
    0.77
    âĶĢâĶĢ
    0.72
    """
    0.71
    -"
    0.68
    -----
    0.66
    Õ
    0.65
    Ñģ
    0.63
     """
    0.63
    ilib
    0.63
    *****
    0.62
    Activations Density 0.178%

    No Known Activations