© 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. 10-RES-JB
    11. 10262
    Prev
    Next
    INDEX
    Explanations

    the German word "einen" and its variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'e'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĥĪ
    -0.62
    SHARE
    -0.61
     Anthem
    -0.60
     Assets
    -0.57
     PEOPLE
    -0.57
     Colleges
    -0.56
     Showdown
    -0.55
     GEAR
    -0.55
    NESS
    -0.55
     Treasure
    -0.54
    POSITIVE LOGITS
    gypt
    1.27
    tymology
    1.27
    ternally
    1.23
    ugen
    1.18
    thereal
    1.11
    agles
    1.09
    got
    1.05
    fter
    1.03
    ller
    1.03
    arthed
    1.00
    Activations Density 0.026%

    No Known Activations