© 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. 23840
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    first-person references and personal experiences

    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
    forcement
    -0.78
    lets
    -0.77
    vert
    -0.71
     Goodbye
    -0.70
    pires
    -0.69
    venge
    -0.67
    kefeller
    -0.65
     Mandatory
    -0.63
    ogue
    -0.63
     goodbye
    -0.63
    POSITIVE LOGITS
    've
    1.26
     haven
    1.15
     hadn
    1.11
    'm
    1.05
     admittedly
    1.02
     already
    0.99
     rarely
    0.99
     didn
    0.98
     cannot
    0.98
     couldn
    0.97
    Activations Density 0.299%

    No Known Activations