© 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. 6-RES-JB
    11. 9965
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person named "Teresa Giudice."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals, likely focusing on personalities or public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.76
    女
    -0.70
     grit
    -0.64
    isky
    -0.64
    psc
    -0.63
    ħĭ
    -0.61
    enment
    -0.60
    days
    -0.59
    GBT
    -0.58
    atures
    -0.58
    POSITIVE LOGITS
    etus
    0.76
    ̶
    0.69
    -$
    0.67
    agall
    0.66
    Container
    0.63
    adr
    0.62
    quote
    0.60
    inately
    0.60
    Ö¼
    0.59
     Caption
    0.59
    Activations Density 0.275%

    No Known Activations