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. 7021
    Prev
    Next
    INDEX
    Explanations

    pronouns related to a group or collective

    oai_token-act-pair · gpt-3.5-turbo

    references to "them" or "Them," indicating a focus on groups or entities being discussed

    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
    âĢ¢âĢ¢
    -0.71
    CCC
    -0.69
    mire
    -0.65
     Salon
    -0.62
     Lori
    -0.59
     Megan
    -0.57
    Line
    -0.57
    JD
    -0.57
     Mansion
    -0.57
    Limit
    -0.56
    POSITIVE LOGITS
    selves
    1.75
     selves
    1.51
    atically
    1.50
    atic
    1.32
    self
    1.19
    atics
    0.85
     individually
    0.84
     themselves
    0.83
    atar
    0.80
    're
    0.78
    Activations Density 0.126%

    No Known Activations