© 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. 1-RES-JB
    11. 10241
    Prev
    Next
    INDEX
    Explanations

    physical measurements such as width, height, weight, and dimensions

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements and specifications related to dimensions, weight, and amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    livion
    -0.84
    olson
    -0.79
    SPONSORED
    -0.74
    romy
    -0.74
    advertisement
    -0.73
    etsy
    -0.72
    all
    -0.72
    ounter
    -0.71
    arb
    -0.71
    ocobo
    -0.71
    POSITIVE LOGITS
     Definition
    1.27
     Dates
    1.16
     Rankings
    1.13
     Locations
    1.13
     Rating
    1.12
     Casting
    1.11
     Parameters
    1.11
     Affect
    1.11
     Plans
    1.11
     Procedures
    1.10
    Activations Density 0.128%

    No Known Activations