© 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. 3072
    Prev
    Next
    INDEX
    Explanations

    words related to proprietary information or exclusive ownership

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to professional sports, particularly football

    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
     ponds
    -0.71
    ById
    -0.67
     pond
    -0.65
    å·
    -0.63
     Stir
    -0.61
     seams
    -0.59
     Dragonbound
    -0.57
    WHERE
    -0.57
     aroused
    -0.57
     paraly
    -0.57
    POSITIVE LOGITS
    imity
    0.95
    etary
    0.94
    incial
    0.92
    ession
    0.90
    agonist
    0.90
    essor
    0.90
    essing
    0.88
    ariat
    0.82
    essional
    0.79
    isher
    0.78
    Activations Density 0.063%

    No Known Activations