© 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 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. 10-RES-JB
    11. 4750
    Prev
    Next
    INDEX
    Explanations

    text related to shopping, promotions, and transactions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gon
    -0.91
     Neon
    -0.90
     Senegal
    -0.88
    anas
    -0.87
     Peck
    -0.87
     Xen
    -0.83
    EN
    -0.83
    Nap
    -0.81
     Jen
    -0.81
     Ezek
    -0.80
    POSITIVE LOGITS
     fisher
    0.90
     Fisher
    0.87
     Coff
    0.84
    cler
    0.80
     logger
    0.78
     saf
    0.77
     Lod
    0.76
    ali
    0.76
     Gear
    0.74
     Casual
    0.73
    Activations Density 0.450%

    No Known Activations