© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11100
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal justice, particularly involving the death penalty

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the death penalty and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uni
    -0.91
     Asus
    -0.78
     Hearth
    -0.76
     Unicorn
    -0.74
    WARN
    -0.74
     Proxy
    -0.73
    ijn
    -0.73
    eting
    -0.72
    nect
    -0.72
    debian
    -0.71
    POSITIVE LOGITS
     sentencing
    1.97
     pard
    1.71
     sentences
    1.67
     parole
    1.65
     convict
    1.62
     sentenced
    1.60
     sentence
    1.59
     punishment
    1.57
     pardon
    1.55
     executions
    1.53
    Activations Density 0.614%

    No Known Activations