© 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. 5909
    Prev
    Next
    INDEX
    Explanations

    locations, such as countries, states, and cities

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and political regions

    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
    Dur
    -0.69
    inventoryQuantity
    -0.66
     Pwr
    -0.61
     Pieces
    -0.61
    clusively
    -0.61
     Ends
    -0.60
     Results
    -0.59
    ILA
    -0.58
    Dialog
    -0.58
    }.
    -0.57
    POSITIVE LOGITS
     reacted
    1.04
     knew
    0.96
     have
    0.95
     complained
    0.95
     are
    0.92
     despise
    0.92
     want
    0.91
     swear
    0.91
     noticed
    0.91
     perceive
    0.90
    Activations Density 0.258%

    No Known Activations