© 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. 9-RES-JB
    11. 11456
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and personal pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating personal relationships or familial connections

    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
    女
    -0.81
    ablishment
    -0.79
    among
    -0.78
    daq
    -0.76
    redits
    -0.76
    aneers
    -0.76
    ancial
    -0.75
    Ô
    -0.74
    ittees
    -0.74
    eware
    -0.72
    POSITIVE LOGITS
     dad
    1.58
     mom
    1.52
     father
    1.51
     mother
    1.49
     parents
    1.47
     grandmother
    1.46
     classmates
    1.45
     roommate
    1.42
     aunt
    1.41
     classmate
    1.34
    Activations Density 0.294%

    No Known Activations