© 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. 9-RES-JB
    11. 7211
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving instructions or command with a slightly aggressive or forceful tone

    oai_token-act-pair · gpt-3.5-turbo

    instances of strong emotional expressions or emphatic statements

    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
     brid
    -0.92
     increasingly
    -0.83
     orient
    -0.82
     disciplines
    -0.81
     mete
    -0.81
     pressing
    -0.78
     inclusion
    -0.78
     ranged
    -0.78
     affili
    -0.77
     revers
    -0.77
    POSITIVE LOGITS
    Advertisements
    1.76
    Conclusion
    1.65
    Related
    1.48
    Here
    1.45
    Bonus
    1.44
    Sources
    1.41
    Contact
    1.41
    Finally
    1.41
    And
    1.41
    References
    1.40
    Activations Density 0.413%

    No Known Activations