© 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. 7-RES-JB
    11. 14189
    Prev
    Next
    INDEX
    Explanations

    mentions of specific measurements of physical spaces in square feet, particularly in relation to buildings and real estate

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of square footage

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    auga
    -0.83
    orea
    -0.75
    inger
    -0.71
    mpeg
    -0.68
    OTOS
    -0.64
    avanaugh
    -0.63
    OPA
    -0.63
    eger
    -0.61
     Rept
    -0.61
    eele
    -0.60
    POSITIVE LOGITS
    ticket
    0.68
    estate
    0.67
    city
    0.67
    Council
    0.67
    Dash
    0.67
    negative
    0.66
    disc
    0.66
     commissions
    0.66
    meter
    0.65
    pound
    0.65
    Activations Density 0.138%

    No Known Activations