© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 3517
    Prev
    Next
    INDEX
    Explanations

    references to the name "Ru"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ruiz."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    £ı
    -0.94
    å§«
    -0.83
    insula
    -0.79
    é¾įå¥ij士
    -0.78
    enegger
    -0.75
     Seym
    -0.73
     SOS
    -0.72
     Cerberus
    -0.72
     GOODMAN
    -0.71
     CPC
    -0.70
    POSITIVE LOGITS
    pees
    1.35
    pee
    1.13
    inous
    1.09
    ined
    0.99
    pt
    0.97
    pless
    0.89
    Ru
    0.89
    pton
    0.89
    gment
    0.89
    aji
    0.89
    Activations Density 0.005%

    No Known Activations