© 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. 373
    Prev
    Next
    INDEX
    Explanations

    special characters and phrases related to data management or coding

    oai_token-act-pair · gpt-3.5-turbo

    special characters and non-standard text representations

    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
    alter
    -0.75
     pigeon
    -0.73
     consolidation
    -0.71
     booster
    -0.70
    uyomi
    -0.70
     Kad
    -0.68
     nodd
    -0.67
     clutter
    -0.67
     Mariners
    -0.66
     sleeper
    -0.66
    POSITIVE LOGITS
    âĤ¬
    1.79
    £
    1.73
    ¢
    1.70
    Ã
    1.66
    Ãī
    1.62
    Ãĥ
    1.60
    Â
    1.59
    ï
    1.57
    ÃĽ
    1.55
    «
    1.52
    Activations Density 0.058%

    No Known Activations