© 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. 11-RES-JB
    11. 7639
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive social impact or community involvement

    oai_token-act-pair · gpt-3.5-turbo

    themes related to societal and environmental awareness

    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
    cott
    -0.70
    azo
    -0.61
    rase
    -0.60
     href
    -0.59
    haar
    -0.57
    henko
    -0.56
    psey
    -0.56
    escription
    -0.56
    eport
    -0.56
    bps
    -0.56
    POSITIVE LOGITS
     itself
    1.28
    osphere
    1.13
     hierarchy
    0.85
    geist
    0.85
     ecosystem
    0.82
    folk
    0.78
     quo
    0.77
     atmosphere
    0.76
    iverse
    0.75
    floor
    0.74
    Activations Density 0.405%

    No Known Activations