© 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. 13824
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or names, especially with the pattern "Br..." and "im"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Br" followed by various letter combinations indicative of names or places

    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
    ĸļ
    -0.89
    ©¶æ
    -0.72
     Reincarn
    -0.64
     seiz
    -0.63
     Uriel
    -0.61
    rogens
    -0.61
     thor
    -0.60
     Shutterstock
    -0.59
     nitrogen
    -0.57
     Gujar
    -0.57
    POSITIVE LOGITS
    sels
    0.98
    swick
    0.94
    itte
    0.93
    gger
    0.89
    zinski
    0.87
    illet
    0.85
    wine
    0.83
    veland
    0.82
    ça
    0.79
    mingham
    0.79
    Activations Density 0.078%

    No Known Activations