© 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. 1-RES-JB
    11. 3764
    Prev
    Next
    INDEX
    Explanations

    phrases expressing preferences for specific things or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "favorite" things or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heed
    -0.83
    aping
    -0.82
    hani
    -0.78
    acial
    -0.78
    urches
    -0.76
    asse
    -0.73
    ural
    -0.73
    thur
    -0.73
    aton
    -0.73
    pex
    -0.72
    POSITIVE LOGITS
     favorite
    1.25
     favorites
    1.03
    favorite
    0.99
    Favorite
    0.97
     Favorite
    0.97
     favourite
    0.96
    é¾įå¥ij士
    0.87
     darling
    0.84
    ="#
    0.82
    ļéĨĴ
    0.82
    Activations Density 0.011%

    No Known Activations