© 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. 13815
    Prev
    Next
    INDEX
    Explanations

    numerical values related to research and data analysis

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to studies and surveys

    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
     Thumbnails
    -0.73
    ufact
    -0.66
    rament
    -0.66
    redits
    -0.65
    ror
    -0.64
    LEASE
    -0.62
    tainment
    -0.61
     Courtesy
    -0.61
    WAR
    -0.60
    Wars
    -0.60
    POSITIVE LOGITS
     randomly
    1.11
     randomized
    1.04
     dataset
    0.98
     prospective
    0.95
     survey
    0.95
     hypothetical
    0.93
     sample
    0.93
     respondents
    0.91
     samples
    0.90
     random
    0.89
    Activations Density 0.169%

    No Known Activations