© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 20549
    Prev
    Next
    INDEX
    Explanations

    locations or addresses mentioned in text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ouses
    -0.79
     hypot
    -0.76
    efully
    -0.74
    phas
    -0.72
    ¾
    -0.70
    ingly
    -0.70
    ilts
    -0.69
    tered
    -0.69
    ulating
    -0.68
    lins
    -0.68
    POSITIVE LOGITS
     Location
    1.27
    Location
    1.12
     Instruments
    0.96
     Locations
    0.95
     Enemies
    0.89
    Reference
    0.87
     Directions
    0.86
     Returning
    0.86
     Lens
    0.86
     Address
    0.84
    Activations Density 0.034%

    No Known Activations