© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10186
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Nike"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Nike brand and its products

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

    No Comments

    Negative Logits
    ulhu
    -0.84
     ILCS
    -0.83
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.73
     miscar
    -0.72
     Liberties
    -0.62
    \\\\\\\\\\\\\\\\
    -0.62
    âĶĢâĶĢ
    -0.61
     loopholes
    -0.61
    operative
    -0.61
    rooms
    -0.61
    POSITIVE LOGITS
     Adidas
    1.05
    idas
    0.97
    mens
    0.92
     sneakers
    0.90
     apparel
    0.89
     Nike
    0.87
     endors
    0.85
     footwear
    0.80
     Sports
    0.79
     shoe
    0.78
    Activations Density 0.010%

    No Known Activations