Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7620
    Prev
    Next
    INDEX
    Explanations

    brand names and product names

    oai_token-act-pair · gpt-3.5-turbo

    specific brands and notable entities, especially in pop culture and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gdala
    -0.76
    razil
    -0.76
    outhern
    -0.75
    rower
    -0.75
    behind
    -0.73
    actionDate
    -0.72
    uckland
    -0.71
    ociate
    -0.71
    starter
    -0.70
    currently
    -0.69
    POSITIVE LOGITS
    ®,
    1.14
     Syndrome
    1.07
     Medals
    1.02
     bulbs
    0.99
     stickers
    0.98
    ®
    0.97
     dolls
    0.96
    âĦ¢
    0.96
     sneakers
    0.94
     commercials
    0.93
    Activations Density 0.493%

    No Known Activations