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. 20251
    Prev
    Next
    INDEX
    Explanations

    web-related terms and actions related to website interaction

    oai_token-act-pair · gpt-3.5-turbo

    references to user interactions and behaviors on websites or platforms

    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
     Disaster
    -0.71
     Immunity
    -0.69
     assass
    -0.68
     Rhodes
    -0.67
     slander
    -0.67
     miracle
    -0.66
     miracles
    -0.66
     tragedies
    -0.65
     fug
    -0.65
     ashes
    -0.64
    POSITIVE LOGITS
     liking
    1.12
     purchasing
    1.10
     browsing
    1.03
     craving
    1.02
     buying
    1.00
     dissatisfied
    0.97
    umers
    0.97
     subscribing
    0.93
     purchases
    0.93
     consume
    0.93
    Activations Density 0.564%

    No Known Activations