© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18266
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of being overly simplified or exaggerated

    oai_token-act-pair · gpt-3.5-turbo

    words related to excess or overabundance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.78
     nomine
    -0.70
    EStream
    -0.69
     Nanto
    -0.66
    zzi
    -0.63
    anwhile
    -0.62
     prosec
    -0.62
     motions
    -0.61
    rica
    -0.60
     theater
    -0.60
    POSITIVE LOGITS
    impl
    1.23
    aturated
    1.01
     overs
    1.00
    amples
    0.95
    leep
    0.94
    ights
    0.87
    ocial
    0.87
    aturation
    0.86
    icro
    0.85
    atur
    0.84
    Activations Density 0.007%

    No Known Activations