© 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. 3-RES-JB
    11. 5276
    Prev
    Next
    INDEX
    Explanations

    the brand "Nike" or related terms

    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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -0.81
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.70
    ÑĮ
    -0.66
     ILCS
    -0.66
    oths
    -0.66
    erest
    -0.64
    operative
    -0.64
    ENCY
    -0.62
     severity
    -0.62
     miscar
    -0.62
    POSITIVE LOGITS
     Adidas
    1.02
     Nike
    0.94
     apparel
    0.89
     endors
    0.88
    idas
    0.88
    mens
    0.86
     sneakers
    0.83
     jerseys
    0.80
     Basketball
    0.77
    ensor
    0.76
    Activations Density 0.006%

    No Known Activations