© 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. 7-RES-JB
    11. 20866
    Prev
    Next
    INDEX
    Explanations

    keywords related to India

    oai_token-act-pair · gpt-3.5-turbo

    references to the Indian context or related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.97
     compr
    -0.82
    EStream
    -0.80
     litter
    -0.78
    è¦ļéĨĴ
    -0.73
     prick
    -0.68
    collection
    -0.67
    TION
    -0.66
    bilt
    -0.66
     depreciation
    -0.65
    POSITIVE LOGITS
    irect
    1.43
    ividually
    1.35
    icative
    1.29
    ebted
    1.26
    ifferent
    1.18
    icator
    1.15
    icates
    1.14
    ications
    1.12
    ivid
    1.11
    oor
    1.10
    Activations Density 0.019%

    No Known Activations