© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16598
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal possessions or activities

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership

    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
    ylum
    -0.89
    Statement
    -0.78
    vernment
    -0.77
    ablishment
    -0.76
    Dialogue
    -0.75
    aneers
    -0.75
    Report
    -0.74
    Crime
    -0.74
    女
    -0.73
    pects
    -0.72
    POSITIVE LOGITS
     favorite
    1.27
     own
    1.23
     favourite
    1.23
     grandma
    1.07
     girlfriend
    1.07
     grandmother
    1.03
     buddy
    1.01
     buddies
    1.00
     friend
    1.00
     dad
    0.98
    Activations Density 0.174%

    No Known Activations