© 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. 16100
    Prev
    Next
    INDEX
    Explanations

    references to charter schools

    oai_token-act-pair · gpt-3.5-turbo

    discussions about charters, particularly in the context of schools or organizations

    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
    utenberg
    -0.79
     Rove
    -0.75
    Downloadha
    -0.70
    nesota
    -0.70
    enez
    -0.70
    ynthesis
    -0.68
    ocate
    -0.67
    ewski
    -0.67
    encers
    -0.65
    ener
    -0.64
    POSITIVE LOGITS
     charter
    0.93
    icut
    0.88
    iffs
    0.83
    iton
    0.73
    iff
    0.72
     Charter
    0.69
     renewal
    0.68
    ions
    0.68
     CLIENT
    0.67
    eer
    0.66
    Activations Density 0.004%

    No Known Activations