© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5010
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, particularly places associated with economic or political discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographical locations or countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    achine
    -0.74
    acter
    -0.73
    ãģĨ
    -0.72
    TAG
    -0.72
    naissance
    -0.70
    Knight
    -0.66
    ault
    -0.66
    »Ĵ
    -0.66
    VIDIA
    -0.65
    ntil
    -0.64
    POSITIVE LOGITS
     GDP
    0.96
     residents
    0.89
     policymakers
    0.87
    ans
    0.85
     electing
    0.81
    ians
    0.78
     citizens
    0.78
     population
    0.76
     taxpayers
    0.76
    's
    0.75
    Activations Density 0.381%

    No Known Activations