© 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. 9-RES-JB
    11. 3193
    Prev
    Next
    INDEX
    Explanations

    abbreviations with the format "a.k.a." and numbers

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to scores and ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.83
    igue
    -0.75
    heit
    -0.71
     guiActiveUn
    -0.61
    ollo
    -0.61
    Cub
    -0.61
    ardo
    -0.60
    ä½ľ
    -0.59
    iosyncr
    -0.57
     Guid
    -0.57
    POSITIVE LOGITS
     Rowling
    0.84
     Vaughan
    0.74
    laus
    0.69
    aid
    0.62
     Chest
    0.62
     Wynne
    0.62
    anga
    0.61
    bye
    0.58
     Gupta
    0.56
    Eh
    0.55
    Activations Density 0.055%

    No Known Activations