© 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. 7-RES-JB
    11. 321
    Prev
    Next
    INDEX
    Explanations

    German words with special characters such as "ä" and "ö"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ä" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORED
    -0.78
    IFIED
    -0.72
     kernels
    -0.68
     Mayweather
    -0.67
     Hodg
    -0.65
     actors
    -0.64
     Jericho
    -0.64
     Sussex
    -0.63
     Canary
    -0.63
     bearer
    -0.62
    POSITIVE LOGITS
    inen
    1.14
    ¢
    1.08
    ä
    1.03
    ternity
    0.99
    nder
    0.96
    ·
    0.93
    tten
    0.91
    ¶
    0.91
    hl
    0.90
    tre
    0.87
    Activations Density 0.023%

    No Known Activations