© 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. 10-RES-JB
    11. 10549
    Prev
    Next
    INDEX
    Explanations

    financial figures and amounts

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newsp
    -0.63
     sizing
    -0.58
     someday
    -0.55
    soDeliveryDate
    -0.54
     specialize
    -0.53
     horm
    -0.51
     Lauder
    -0.50
     respons
    -0.49
     boun
    -0.49
     spokes
    -0.48
    POSITIVE LOGITS
    287
    1.03
    257
    0.97
    267
    0.93
    261
    0.93
    293
    0.92
    298
    0.92
    376
    0.91
    297
    0.91
    258
    0.91
    193
    0.91
    Activations Density 0.220%

    No Known Activations