© 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. 4-RES-JB
    11. 19534
    Prev
    Next
    INDEX
    Explanations

    references to specific geographic locations, particularly focused on Nova Scotia

    oai_token-act-pair · gpt-3.5-turbo

    references to the regions of Nova Scotia and New Brunswick

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

    No Comments

    Negative Logits
    hner
    -0.81
    growth
    -0.70
    ebus
    -0.70
    angel
    -0.69
    aquin
    -0.66
    HO
    -0.66
    æł
    -0.64
    Jump
    -0.62
    abase
    -0.61
    never
    -0.61
    POSITIVE LOGITS
     Scotia
    1.40
     Harbour
    0.95
    foundland
    0.92
     Yard
    0.89
     Confederation
    0.88
     Royale
    0.80
     Newfoundland
    0.80
     Downs
    0.79
     Telecom
    0.77
     Mississ
    0.77
    Activations Density 0.017%

    No Known Activations