© 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. 4-RES-JB
    11. 632
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical or emotional restraint

    oai_token-act-pair · gpt-3.5-turbo

    mentions and variations of the word "restraint."

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

    No Comments

    Negative Logits
    dule
    -0.73
     Blessed
    -0.73
    istle
    -0.70
    ynt
    -0.69
    mitt
    -0.68
    mberg
    -0.67
    OLOGY
    -0.66
    eday
    -0.65
    pp
    -0.64
     Printing
    -0.64
    POSITIVE LOGITS
     restraint
    1.08
    raint
    1.05
     restrain
    0.92
     restraints
    0.90
    estinal
    0.86
     actionGroup
    0.84
     restraining
    0.81
     sidx
    0.80
    raints
    0.79
     breathing
    0.76
    Activations Density 0.013%

    No Known Activations