© 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. 0-RES-JB
    11. 15620
    Prev
    Next
    INDEX
    Explanations

    words related to significant changes or transformations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restructuring and reshaping processes

    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
    mberg
    -0.76
    ports
    -0.75
    FIELD
    -0.75
    PORT
    -0.69
     Cel
    -0.68
    urance
    -0.67
     Labrador
    -0.66
    ostic
    -0.66
    ileged
    -0.65
     Bowling
    -0.65
    POSITIVE LOGITS
     resh
    4.03
     reorgan
    1.83
     restructuring
    1.66
     rearr
    1.60
     shuffle
    1.45
     restruct
    1.44
     rewrite
    1.44
     rewriting
    1.38
     remod
    1.34
     remake
    1.33
    Activations Density 0.034%

    No Known Activations