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. 19458
    Prev
    Next
    INDEX
    Explanations

    product-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Product" in various contexts associated with updates and descriptions

    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
     Blaz
    -0.68
    trop
    -0.67
     Brother
    -0.63
     Leone
    -0.61
     Peninsula
    -0.60
    QUEST
    -0.60
    CLASSIFIED
    -0.59
     lone
    -0.58
    asons
    -0.57
     Soros
    -0.57
    POSITIVE LOGITS
    ivity
    1.53
    ively
    1.37
    ivities
    1.23
    iveness
    1.12
    ions
    0.89
     packaging
    0.89
    Hunt
    0.86
    ivism
    0.86
    urers
    0.84
    istry
    0.82
    Activations Density 0.024%

    No Known Activations