© 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. 0-RES-JB
    11. 15390
    Prev
    Next
    INDEX
    Explanations

    brands of sports apparel

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nike brand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gal
    -0.86
    agh
    -0.74
     ter
    -0.72
    mins
    -0.71
    ECT
    -0.68
     procedural
    -0.65
     bot
    -0.64
    anch
    -0.64
     intr
    -0.63
     processing
    -0.62
    POSITIVE LOGITS
     Nike
    3.83
     Adidas
    2.82
    idas
    2.05
     sneakers
    1.65
     footwear
    1.47
    sole
    1.44
     Pepsi
    1.42
     Hyundai
    1.37
     apparel
    1.33
     Shoes
    1.32
    Activations Density 0.020%

    No Known Activations