© 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. 10313
    Prev
    Next
    INDEX
    Explanations

    commands or instructions urging someone to stop a particular action or behavior

    oai_token-act-pair · gpt-3.5-turbo

    commands related to halting actions or behaviors

    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
    ii
    -0.66
     bonded
    -0.65
     possessed
    -0.65
    arial
    -0.65
     flesh
    -0.64
    iaries
    -0.63
     arche
    -0.62
     obliged
    -0.61
     deposition
    -0.61
     bos
    -0.61
    POSITIVE LOGITS
     Stop
    3.82
    Stop
    2.82
    stop
    2.38
     STOP
    2.37
     stop
    2.03
     stops
    1.61
     stopping
    1.39
     stopped
    1.32
     Quit
    1.28
     halt
    1.24
    Activations Density 0.009%

    No Known Activations