© 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. 11-RES-JB
    11. 7002
    Prev
    Next
    INDEX
    Explanations

    words related to kitchen items or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to kitchens in various contexts

    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
     Trooper
    -0.69
     trooper
    -0.68
     Bonds
    -0.68
    iates
    -0.64
    orb
    -0.63
    iations
    -0.63
    ————
    -0.63
     Investor
    -0.62
    worthiness
    -0.62
    reon
    -0.62
    POSITIVE LOGITS
    ware
    1.15
    ette
    1.08
    washer
    1.05
    Aid
    1.01
    cook
    0.99
     appliances
    0.97
    tops
    0.94
     stove
    0.94
     appliance
    0.92
    ettes
    0.92
    Activations Density 0.066%

    No Known Activations