© 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. 2-RES-JB
    11. 3796
    Prev
    Next
    INDEX
    Explanations

    phrases related to the abbreviation "Ind."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "India" or related terms

    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
    EStream
    -0.91
    sonian
    -0.91
    thodox
    -0.79
     compr
    -0.77
    BILITIES
    -0.76
    acters
    -0.74
    avorite
    -0.74
    enegger
    -0.73
    olitan
    -0.70
    bley
    -0.68
    POSITIVE LOGITS
    irect
    1.14
    ividually
    1.08
    ebted
    1.03
    icator
    0.99
    icative
    0.97
    enture
    0.93
    epend
    0.93
    icates
    0.87
    icators
    0.86
    ifferent
    0.86
    Activations Density 0.008%

    No Known Activations