© 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. 7098
    Prev
    Next
    INDEX
    Explanations

    references to article sections/lists

    oai_token-act-pair · gpt-3.5-turbo

    highlighted notes or important points in a text

    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
     whoever
    -0.60
    Brien
    -0.59
     nurt
    -0.57
    existent
    -0.57
    Whoever
    -0.56
    adle
    -0.55
     conscientious
    -0.55
     seizing
    -0.55
    Luckily
    -0.55
     confid
    -0.54
    POSITIVE LOGITS
     PDF
    1.01
     FAQ
    1.00
     screenshots
    0.94
     Downloads
    0.93
     pdf
    0.92
     Transcript
    0.91
     annotations
    0.91
     descriptions
    0.89
     downloadable
    0.88
     Contents
    0.88
    Activations Density 0.423%

    No Known Activations