© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2780
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to court cases or rulings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" followed by varying contexts or descriptors

    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
    facts
    -0.77
    Contents
    -0.76
    tarians
    -0.76
    grounds
    -0.75
    Enjoy
    -0.75
    words
    -0.75
    iments
    -0.73
     è£ıè
    -0.71
    agree
    -0.71
    soType
    -0.69
    POSITIVE LOGITS
     slew
    1.21
     spate
    1.16
     scathing
    1.06
     controversial
    1.05
     trio
    1.04
     trove
    1.04
     whopping
    1.00
     landmark
    1.00
     consortium
    0.99
     flurry
    0.99
    Activations Density 0.334%

    No Known Activations