Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 21803
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals named "Lewandowski" and "ettel"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly Corey Lewandowski and Anthony Ettel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.91
    creen
    -0.79
    netflix
    -0.76
    ulhu
    -0.74
    utical
    -0.71
    uity
    -0.71
    iasco
    -0.69
    cone
    -0.69
    istries
    -0.68
    matic
    -0.67
    POSITIVE LOGITS
    uder
    1.10
    andowski
    0.89
     Auschwitz
    0.71
     Gaal
    0.68
     ger
    0.65
    ipal
    0.64
    ploy
    0.64
    erers
    0.64
     Rubin
    0.63
    aging
    0.63
    Activations Density 0.016%

    No Known Activations