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

    Neuronpedia

    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. 1-RES-JB
    11. 11700
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Halifax

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Halifax

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    holding
    -0.76
    Loading
    -0.76
    ktop
    -0.74
    oly
    -0.73
     Izan
    -0.73
    lihood
    -0.72
    ech
    -0.70
    ures
    -0.69
    ept
    -0.68
    eem
    -0.68
    POSITIVE LOGITS
    ifax
    1.32
     Halifax
    1.21
     Scotia
    0.96
     Dartmouth
    0.82
     Harbour
    0.79
    ricanes
    0.77
    icut
    0.73
     Bridgewater
    0.70
    imore
    0.69
     Yards
    0.67
    Activations Density 0.007%

    No Known Activations