© 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. 0-RES-JB
    11. 16135
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "traditional."

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional methods or practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.70
    20439
    -0.69
    soever
    -0.68
    agically
    -0.66
    hots
    -0.65
    about
    -0.64
     mysteriously
    -0.64
    Ń·
    -0.64
    netflix
    -0.64
     Lynd
    -0.64
    POSITIVE LOGITS
    Traditional
    2.47
     Traditional
    0.94
    TEXTURE
    0.89
    rawdownloadcloneembedreportprint
    0.77
    Reloaded
    0.72
    Improved
    0.68
     Flavoring
    0.67
    Urban
    0.66
     cuisine
    0.66
    Thom
    0.64
    Activations Density 0.002%

    No Known Activations