© 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. 1420
    Prev
    Next
    INDEX
    Explanations

    references to physical or metaphorical forms of restraint

    oai_token-act-pair · gpt-3.5-turbo

    references to restraint, particularly in contexts involving control or limitations

    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
     Running
    -0.73
     AIDS
    -0.67
    Wiki
    -0.65
    beck
    -0.64
     Behind
    -0.64
     Cancer
    -0.63
    ydia
    -0.62
    SS
    -0.61
    ide
    -0.61
    buck
    -0.61
    POSITIVE LOGITS
     restraint
    3.32
     restraints
    2.36
    raint
    1.54
     restrain
    1.45
     restrained
    1.24
    raints
    1.17
    folio
    0.97
     caution
    0.91
     moderation
    0.83
     cessation
    0.83
    Activations Density 0.007%

    No Known Activations