© 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. 4610
    Prev
    Next
    INDEX
    Explanations

    information related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    factual information about countries and their historical 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
    NFL
    -0.94
    upiter
    -0.88
    Tesla
    -0.88
    Batman
    -0.83
    Lock
    -0.82
    FBI
    -0.81
    APD
    -0.78
    ueller
    -0.78
    UFC
    -0.76
    NSA
    -0.75
    POSITIVE LOGITS
     ethn
    1.40
     ethnic
    1.39
     indigenous
    1.34
     colonial
    1.22
     Ethnic
    1.22
     UNESCO
    1.21
     colonialism
    1.21
     Albania
    1.20
     migrant
    1.19
     Armenia
    1.19
    Activations Density 0.877%

    No Known Activations