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. 13773
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Cruz

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cruz."

    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
     à¨
    -0.74
     Seym
    -0.72
    ebin
    -0.70
     Finnish
    -0.70
    ochemical
    -0.66
    OX
    -0.66
     Bulgarian
    -0.66
    ש
    -0.65
    olitan
    -0.63
    Ö¼
    -0.61
    POSITIVE LOGITS
    Cruz
    1.22
     Cruz
    1.19
    omics
    0.86
     Rubio
    0.82
    itus
    0.77
     Rafael
    0.75
     Ramos
    0.74
    ville
    0.73
    zon
    0.72
    esque
    0.71
    Activations Density 0.006%

    No Known Activations