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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12488
    Prev
    Next
    INDEX
    Explanations

    proper nouns or named entities, particularly focusing on the name "Wally."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names related to people, organizations, and notable entities

    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
    lege
    -0.86
    osi
    -0.83
    gee
    -0.75
    osa
    -0.75
    ivably
    -0.72
    olla
    -0.68
    bler
    -0.68
    lesi
    -0.67
    ving
    -0.67
     Spa
    -0.67
    POSITIVE LOGITS
    peed
    0.87
    andise
    0.86
    hest
    0.72
    åħī
    0.70
    ifiable
    0.67
     Cornel
    0.67
    np
    0.67
     Carbuncle
    0.66
    mil
    0.65
    ocobo
    0.65
    Activations Density 0.017%

    No Known Activations