© 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. 10-RES-JB
    11. 13721
    Prev
    Next
    INDEX
    Explanations

    prompts asking for opinions, thoughts, influences, or experiences

    oai_token-act-pair · gpt-3.5-turbo

    questions that inquire about personal experiences or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geoning
    -0.80
    alde
    -0.77
    het
    -0.77
    wald
    -0.73
    oval
    -0.72
    ammed
    -0.69
    overe
    -0.69
    aea
    -0.68
    avage
    -0.68
    osta
    -0.68
    POSITIVE LOGITS
     favourite
    1.23
     favorite
    1.17
     Favorite
    1.15
    Favorite
    1.12
     hobbies
    1.00
     favourites
    0.94
     favorites
    0.93
     coolest
    0.92
     misconceptions
    0.90
     inspir
    0.87
    Activations Density 0.172%

    No Known Activations