© 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. 2-RES-JB
    11. 9574
    Prev
    Next
    INDEX
    Explanations

    references to rural areas and locations

    oai_token-act-pair · gpt-3.5-turbo

    references to rural areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipedia
    -0.81
    erion
    -0.80
    wcsstore
    -0.78
    ophen
    -0.74
    argon
    -0.74
    agame
    -0.74
    inventoryQuantity
    -0.74
    NSA
    -0.73
    POS
    -0.72
    emis
    -0.71
    POSITIVE LOGITS
     rural
    0.99
     Rural
    0.98
     villages
    0.87
     countryside
    0.83
     Roads
    0.78
     forest
    0.77
     estates
    0.77
     peasant
    0.76
     dwellings
    0.75
     wilderness
    0.74
    Activations Density 0.011%

    No Known Activations