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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 2355
    Prev
    Next
    INDEX
    Explanations

    people or groups followed by actions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or individuals defined by the word "who"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fresh
    -0.64
     Shake
    -0.63
    >>>>>>>>
    -0.63
     Birds
    -0.59
    LAN
    -0.59
    fresh
    -0.58
    hander
    -0.58
     drying
    -0.56
    Fresh
    -0.56
     Craw
    -0.56
    POSITIVE LOGITS
     oppose
    1.03
     partake
    0.95
     criticize
    0.94
     benefited
    0.93
     succeed
    0.92
     prevail
    0.88
     survived
    0.87
     specialize
    0.87
     argue
    0.85
     perished
    0.84
    Activations Density 0.130%

    No Known Activations