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. 18774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership or belonging

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ownership or possession

    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
    imar
    -0.70
     Hurricanes
    -0.64
    olson
    -0.63
    iling
    -0.59
    urnal
    -0.59
    iled
    -0.59
     Farming
    -0.56
    aptic
    -0.56
    ils
    -0.56
    annis
    -0.56
    POSITIVE LOGITS
    holders
    0.81
    ĪĴ
    0.79
    BuyableInstoreAndOnline
    0.77
    Interstitial
    0.76
    itialized
    0.76
     exclusively
    0.76
    holder
    0.73
    itaire
    0.72
     belong
    0.70
     belongs
    0.70
    Activations Density 0.032%

    No Known Activations