© 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. 23782
    Prev
    Next
    INDEX
    Explanations

    proper nouns or brand names

    oai_token-act-pair · gpt-3.5-turbo

    the word "The" in various contexts

    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
    orate
    -1.03
    Population
    -0.84
    Jews
    -0.83
    AIDS
    -0.79
    Muslims
    -0.79
    racial
    -0.79
    lie
    -0.75
    ictions
    -0.75
    ornings
    -0.75
    perse
    -0.74
    POSITIVE LOGITS
     latter
    1.12
     aforementioned
    1.06
     cheapest
    1.05
     latest
    1.03
     newest
    1.01
     sleek
    1.01
     Snapdragon
    1.00
     smallest
    0.99
     venerable
    0.98
     slightest
    0.96
    Activations Density 0.325%

    No Known Activations