© 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. 12-RES-JB
    11. 4367
    Prev
    Next
    INDEX
    Explanations

    mentions of policy decisions, government actions, and legal issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    conjunctions and phrases indicating obligation or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Gleaming
    -0.69
    æĪ¦
    -0.68
    advertisement
    -0.67
    iHUD
    -0.67
    ideshow
    -0.65
    paralle
    -0.65
    asher
    -0.64
    ipel
    -0.63
    Winged
    -0.63
    oké
    -0.62
    POSITIVE LOGITS
     SHOULD
    1.10
     ought
    1.06
     should
    1.01
     shouldn
    0.98
    should
    0.95
     cannot
    0.87
     WILL
    0.84
     MUST
    0.83
     unwilling
    0.80
    will
    0.78
    Activations Density 0.057%

    No Known Activations