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. 8-RES-JB
    6. 1449
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the texture and taste of food and beverages

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives related to texture and flavor in food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.84
     guiActiveUn
    -0.79
    emis
    -0.79
    quest
    -0.78
    redit
    -0.76
    eligible
    -0.74
    Attempt
    -0.73
    isphere
    -0.73
    registered
    -0.71
    ploma
    -0.70
    POSITIVE LOGITS
    ness
    1.32
    nesses
    1.06
     metallic
    1.03
    ened
    1.00
     organic
    0.96
     texture
    0.94
    ener
    0.93
    ening
    0.92
     nature
    0.91
     creamy
    0.89
    Activations Density 0.170%

    No Known Activations