© 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. 2235
    Prev
    Next
    INDEX
    Explanations

    numerical descriptions of length, specifically in terms of the number of pages

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number of pages in documents or books

    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
    oÄŁ
    -0.87
    ecast
    -0.79
    operator
    -0.73
    ereo
    -0.70
    alore
    -0.70
     Osiris
    -0.70
    âĹ¼
    -0.67
     Rivals
    -0.66
    prus
    -0.66
    Ħ¢
    -0.65
    POSITIVE LOGITS
     detailing
    1.02
     manuscript
    1.01
     handwritten
    0.98
     pages
    0.94
     outlining
    0.94
     pdf
    0.92
     redacted
    0.90
     PDF
    0.89
     booklet
    0.88
     document
    0.88
    Activations Density 0.042%

    No Known Activations