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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 19317
    Prev
    Next
    INDEX
    Explanations

    references to eating or food-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of eating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stellar
    -0.79
     Gemini
    -0.78
    channelAvailability
    -0.75
     Aus
    -0.73
     Lash
    -0.68
     PV
    -0.68
    worthiness
    -0.67
     Stra
    -0.66
     Nich
    -0.65
     Constable
    -0.64
    POSITIVE LOGITS
     habits
    1.06
    eteria
    1.03
     eaten
    0.96
     eat
    0.92
     foods
    0.91
     breakfast
    0.91
     meals
    0.87
    anut
    0.86
    ibal
    0.86
    essen
    0.85
    Activations Density 0.030%

    No Known Activations