© 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. 20510
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to sports performances

    oai_token-act-pair · gpt-3.5-turbo

    financial metrics and statistics

    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
     Cue
    -0.67
     abroad
    -0.63
     indirect
    -0.62
     overdue
    -0.62
     Fundamental
    -0.61
     Deng
    -0.61
     Wonderland
    -0.60
     today
    -0.60
     flight
    -0.58
     Universal
    -0.58
    POSITIVE LOGITS
    359
    1.41
    393
    1.39
    411
    1.39
    356
    1.37
    355
    1.37
    373
    1.36
    363
    1.36
    439
    1.36
    343
    1.35
    377
    1.35
    Activations Density 0.028%

    No Known Activations