© 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. 14841
    Prev
    Next
    INDEX
    Explanations

    references to items found in a kitchen

    oai_token-act-pair · gpt-3.5-turbo

    references to kitchens and related spaces

    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
    âĢ¢âĢ¢
    -0.76
    ullah
    -0.74
     Trooper
    -0.73
     USAF
    -0.69
    utic
    -0.68
    inant
    -0.64
    idas
    -0.63
    RAY
    -0.63
     Yanuk
    -0.62
    POS
    -0.62
    POSITIVE LOGITS
     cabinets
    0.92
    washer
    0.89
     sink
    0.88
     cooks
    0.87
    ware
    0.86
     kitchens
    0.86
    tops
    0.85
     kitchen
    0.84
    nut
    0.83
     appliance
    0.82
    Activations Density 0.013%

    No Known Activations