© 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. 1-RES-JB
    11. 3905
    Prev
    Next
    INDEX
    Explanations

    French words with accented characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "ét" in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vasive
    -0.71
     Exc
    -0.69
     Apollo
    -0.67
    kernel
    -0.64
     stock
    -0.64
    frame
    -0.64
    lime
    -0.61
    birth
    -0.61
    tree
    -0.60
     Captain
    -0.60
    POSITIVE LOGITS
    ét
    1.24
    roit
    1.00
    ablish
    0.95
    iquette
    0.93
    itle
    0.90
    é
    0.89
    itles
    0.87
    én
    0.86
    ité
    0.84
    ues
    0.83
    Activations Density 0.005%

    No Known Activations