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

    Neuronpedia

    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. 9-RES-JB
    11. 7583
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns, specifically "my."

    oai_token-act-pair · gpt-3.5-turbo

    references to the first person possessive pronoun "my"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apiece
    -0.86
    itect
    -0.74
     respectively
    -0.73
    ibaba
    -0.68
    illac
    -0.64
    heads
    -0.64
     yourselves
    -0.64
     guiIcon
    -0.63
    etz
    -0.62
    idates
    -0.62
    POSITIVE LOGITS
    anmar
    1.31
    stery
    1.23
     own
    1.18
     wife
    1.11
     husband
    1.11
    opic
    1.10
    ocard
    1.09
     favorite
    1.09
     dad
    1.08
    opia
    1.05
    Activations Density 0.136%

    No Known Activations