© 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. 2-RES-JB
    11. 338
    Prev
    Next
    INDEX
    Explanations

    the term "lakh" used in numerical contexts

    oai_token-act-pair · gpt-4-turbo

    phrases related to specific numerical figures typically involving financial amounts

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical values, specifically large quantities

    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
    gotten
    -0.74
    bidden
    -0.65
     nonex
    -0.64
     envy
    -0.63
    changes
    -0.61
    eve
    -0.60
    POS
    -0.60
    FIN
    -0.60
    fruit
    -0.59
    ces
    -0.59
    POSITIVE LOGITS
     crore
    1.46
     lakh
    0.89
     litres
    0.88
     Nadu
    0.85
    ï¸ı
    0.85
    ombat
    0.84
     hectares
    0.84
     ILCS
    0.84
    nir
    0.82
    s
    0.81
    Activations Density 0.003%

    No Known Activations