© 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. 25
    Prev
    Next
    INDEX
    Explanations

    email addresses containing 'ich' or 'ech'

    oai_token-act-pair · gpt-3.5-turbo

    numerical and financial information

    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
    alo
    -0.92
     Allison
    -0.90
    atto
    -0.88
     Lor
    -0.84
     Laur
    -0.83
     Odin
    -0.81
     Angola
    -0.81
    ilon
    -0.80
     lesbian
    -0.80
     Toledo
    -0.79
    POSITIVE LOGITS
    ich
    1.15
    uch
    1.00
    stress
    0.93
    uchin
    0.90
     Ich
    0.88
    ster
    0.87
     Nicholson
    0.87
    59
    0.87
    ester
    0.86
    ech
    0.85
    Activations Density 0.510%

    No Known Activations