© 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. 2-RES-JB
    11. 23842
    Prev
    Next
    INDEX
    Explanations

    words related to leniency, toughness, and draconian measures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal leniency and strictness in enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rift
    -0.83
    Rus
    -0.79
    thora
    -0.76
    wash
    -0.75
    Sphere
    -0.74
    plane
    -0.70
     Corpse
    -0.70
     Canterbury
    -0.69
    ieu
    -0.68
     Feast
    -0.68
    POSITIVE LOGITS
     vetting
    1.04
     stringent
    1.02
     toug
    0.98
     restrictive
    0.95
     punitive
    0.94
     stricter
    0.90
     tougher
    0.89
     harsher
    0.88
     sentencing
    0.88
     deported
    0.87
    Activations Density 0.021%

    No Known Activations