© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6-RES-JB
    11. 1551
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations or political jurisdictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to territory, nationality, and legal authorization in relation to different 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
    rieg
    -0.70
    urger
    -0.69
    develop
    -0.68
    usters
    -0.64
    onge
    -0.64
    KING
    -0.64
    Said
    -0.63
    Ut
    -0.62
    yss
    -0.62
    struct
    -0.61
    POSITIVE LOGITS
    azeera
    0.89
    isine
    0.70
    tops
    0.69
    ombat
    0.66
    grounds
    0.66
     consulate
    0.66
     abroad
    0.66
    tones
    0.65
    renheit
    0.63
    icals
    0.63
    Activations Density 0.350%

    No Known Activations