© 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 EvalsExportsinterp-engineNEWAPI 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. 19040
    Prev
    Next
    INDEX
    Explanations

    street addresses, particularly with block numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with addresses or locations

    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
    uddenly
    -0.69
     Warfare
    -0.63
    quickShipAvailable
    -0.62
    itu
    -0.62
     coron
    -0.61
    nings
    -0.60
    better
    -0.60
    alyses
    -0.60
    aunders
    -0.59
    idon
    -0.58
    POSITIVE LOGITS
     pound
    1.07
    lb
    1.06
     acre
    1.04
     mile
    0.99
     sq
    0.99
    sq
    0.96
     block
    0.89
    mAh
    0.84
     meter
    0.83
     lb
    0.83
    Activations Density 0.072%

    No Known Activations