© 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. 3-RES-JB
    11. 552
    Prev
    Next
    INDEX
    Explanations

    superlatives indicating a high level of something

    oai_token-act-pair · gpt-3.5-turbo

    words that emphasize an extreme degree of quality or characteristic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.80
     Procedures
    -0.72
    Posts
    -0.69
    ocene
    -0.69
     Pages
    -0.67
     Procedure
    -0.66
     screenings
    -0.66
     Picks
    -0.65
    eer
    -0.65
     Pavilion
    -0.65
    POSITIVE LOGITS
     appreciated
    0.78
    initions
    0.72
    DonaldTrump
    0.70
     qualified
    0.69
    overe
    0.69
     appreciate
    0.69
     fulfilled
    0.68
     assimil
    0.66
    soType
    0.66
     accomplished
    0.66
    Activations Density 0.010%

    No Known Activations