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. 3-RES-JB
    6. 21405
    Prev
    Next
    INDEX
    Explanations

    mentions of the brand "Soylent"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific brands or products, particularly related to food or culinary items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sight
    -0.70
    iscopal
    -0.69
     disenfranch
    -0.68
    ulhu
    -0.67
    asper
    -0.67
    isms
    -0.66
     haunt
    -0.65
    DCS
    -0.64
    merce
    -0.64
    inational
    -0.64
    POSITIVE LOGITS
     Soy
    0.97
    lio
    0.90
    lings
    0.87
    bean
    0.83
    bits
    0.81
    uz
    0.80
    tis
    0.80
    ovy
    0.78
    akov
    0.78
    chenko
    0.77
    Activations Density 0.011%

    No Known Activations