© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20866
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their correlation with authority or roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -0.73
    ablishment
    -0.66
     externalToEVAOnly
    -0.66
    nesty
    -0.65
    BALL
    -0.64
    pering
    -0.63
    ixon
    -0.63
    uph
    -0.62
    tenance
    -0.62
    vier
    -0.62
    POSITIVE LOGITS
     newfound
    1.20
     clout
    1.14
     own
    1.00
     imagination
    1.00
     discretion
    0.99
     leverage
    0.99
     expertise
    0.96
     considerable
    0.94
     fists
    0.90
     powers
    0.89
    Activations Density 0.078%

    No Known Activations