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. 7-RES-JB
    6. 15539
    Prev
    Next
    INDEX
    Explanations

    customers who are possibly willing to buy or line up for a product

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of people involved in consumer or user activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sole
    -0.67
    Accessory
    -0.64
    iasis
    -0.62
    achment
    -0.62
     behalf
    -0.61
    ces
    -0.60
    DOWN
    -0.58
    ttp
    -0.58
    YL
    -0.57
    ;;;;;;;;;;;;
    -0.56
    POSITIVE LOGITS
     beware
    0.99
    hip
    0.88
     everywhere
    0.85
     aren
    0.81
    hips
    0.78
     are
    0.77
    aurus
    0.76
     weren
    0.76
    paces
    0.76
     reacted
    0.74
    Activations Density 0.310%

    No Known Activations