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

    Neuronpedia

    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. 11-RES-JB
    11. 21854
    Prev
    Next
    INDEX
    Explanations

    phrases related to purchasing or buying various items and products

    oai_token-act-pair · gpt-3.5-turbo

    references to purchasing and buying items or services

    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
     disciplinary
    -0.68
    ciplinary
    -0.63
     mischief
    -0.60
     eruption
    -0.60
     eru
    -0.60
    athi
    -0.59
     relevance
    -0.58
     forceful
    -0.58
     severity
    -0.58
    mber
    -0.57
    POSITIVE LOGITS
     cheaply
    1.42
     outright
    1.12
     wholesale
    1.11
     priced
    1.08
     cheaper
    1.05
     online
    1.05
     cheapest
    0.98
     coupons
    0.96
     cheap
    0.95
     separately
    0.94
    Activations Density 0.325%

    No Known Activations