© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16750
    Prev
    Next
    INDEX
    Explanations

    phrases related to penalties

    oai_token-act-pair · gpt-3.5-turbo

    references to penalties or punishments

    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
    echo
    -0.68
     Chest
    -0.67
     Evangel
    -0.67
     articulated
    -0.63
    ocal
    -0.62
     Tuls
    -0.62
    Pop
    -0.61
    Pic
    -0.60
     geek
    -0.60
     KH
    -0.59
    POSITIVE LOGITS
     penalties
    3.98
     penalty
    2.81
     punishments
    2.27
     Penalty
    2.25
     fines
    1.87
     punishment
    1.68
     penal
    1.64
     sanctions
    1.58
     bonuses
    1.50
     prohibitions
    1.44
    Activations Density 0.015%

    No Known Activations