© 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. 9-RES-JB
    11. 7363
    Prev
    Next
    INDEX
    Explanations

    verbs related to legal action and physical actions, particularly involving force or harm

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to judgment and sentencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĨĴ
    -0.75
     Contributions
    -0.73
     Previous
    -0.71
     Citizen
    -0.70
     UA
    -0.68
    heard
    -0.67
    ongo
    -0.67
     Horizons
    -0.67
     Emerging
    -0.67
     Bulletin
    -0.66
    POSITIVE LOGITS
     imprison
    1.22
     incarcer
    1.13
     handc
    1.10
     confisc
    1.10
     remove
    1.03
     punish
    1.03
     forcibly
    0.98
     deport
    0.97
     humili
    0.97
     bury
    0.97
    Activations Density 0.478%

    No Known Activations