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. 0-RES-JB
    6. 3633
    Prev
    Next
    INDEX
    Explanations

    instances of the name "Lopez" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the surname "Lopez" and associated content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sham
    -0.67
    abled
    -0.67
    URA
    -0.67
     qual
    -0.64
     pitches
    -0.64
     pitch
    -0.64
    urances
    -0.64
    pub
    -0.64
     Investig
    -0.63
    urable
    -0.63
    POSITIVE LOGITS
     Lopez
    3.60
    opez
    1.60
     McL
    1.17
     Larson
    1.04
     Perez
    0.95
     Rivera
    0.93
     Nets
    0.92
     Zimmerman
    0.90
     Weiner
    0.89
     Lars
    0.87
    Activations Density 0.020%

    No Known Activations