© 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. 22191
    Prev
    Next
    INDEX
    Explanations

    phrases related to quotes or statements by particular individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals and their roles or actions in a narrative context

    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
     storefront
    -0.76
     rotation
    -0.75
     paperback
    -0.74
     handheld
    -0.74
     setting
    -0.73
     decomp
    -0.73
     recycling
    -0.72
     subdivision
    -0.72
     yield
    -0.72
     circulation
    -0.72
    POSITIVE LOGITS
    Wilson
    1.35
    ï¸ı
    1.27
    Connor
    1.20
    Jr
    1.15
    Jones
    1.13
    Smith
    1.12
    Murray
    1.11
    Lewis
    1.11
    Ol
    1.11
    Hay
    1.09
    Activations Density 0.192%

    No Known Activations