© 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 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. 10-RES-JB
    11. 4685
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific geographical location, possibly related to politics or news

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Northern" in various contexts

    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
    awaru
    -0.86
    ifice
    -0.78
    endi
    -0.77
    inventoryQuantity
    -0.74
    ulative
    -0.74
    transform
    -0.72
    atically
    -0.70
    ulous
    -0.69
    uality
    -0.69
    acl
    -0.68
    POSITIVE LOGITS
     Hemisphere
    1.31
     hemisphere
    1.18
     Lights
    1.14
     Ireland
    1.09
     Liberties
    1.02
     Territory
    0.98
     Caucasus
    0.92
     Territories
    0.87
    most
    0.86
     Exposure
    0.86
    Activations Density 0.028%

    No Known Activations