Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 9089
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and possessive forms indicating ownership or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edd
    -0.72
    atever
    -0.63
     Airl
    -0.62
    ypes
    -0.60
     Beg
    -0.59
     IPM
    -0.59
    ologne
    -0.59
    aiman
    -0.58
    olics
    -0.58
    itement
    -0.56
    POSITIVE LOGITS
    selves
    1.29
    self
    1.24
    creen
    0.88
    field
    0.77
    fields
    0.77
    opia
    0.76
    !/
    0.72
     selves
    0.69
    ovie
    0.67
    craft
    0.66
    Activations Density 0.031%

    No Known Activations