© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 4520
    Prev
    Next
    INDEX
    Explanations

    proper names "Luis" with varying activations, likely associated with different individuals or contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Luis."

    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
    BOOK
    -0.83
    skirts
    -0.82
    schild
    -0.77
    mother
    -0.76
    ulhu
    -0.74
    swing
    -0.73
    enegger
    -0.73
    fare
    -0.70
    outer
    -0.70
    ocrine
    -0.69
    POSITIVE LOGITS
     Luis
    1.20
     Suarez
    1.05
     Enrique
    1.00
     Carlos
    0.93
     Fernando
    0.90
     Gomez
    0.90
     Mu
    0.83
     Antonio
    0.83
     Gerrard
    0.82
     Rey
    0.79
    Activations Density 0.003%

    No Known Activations