© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19642
    Prev
    Next
    INDEX
    Explanations

    names or words related to a physical location, specifically piers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific locations or places, particularly related to "Pier."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bihar
    -0.78
    avez
    -0.71
    mson
    -0.67
    elta
    -0.66
    organic
    -0.64
    STEP
    -0.63
    ä
    -0.62
    ether
    -0.62
    arily
    -0.61
     Universities
    -0.61
    POSITIVE LOGITS
     pier
    1.17
     Pier
    1.16
    rette
    0.85
    cer
    0.83
    asus
    0.80
    acers
    0.79
    idon
    0.79
     Borough
    0.79
    cers
    0.79
    achy
    0.77
    Activations Density 0.012%

    No Known Activations