© 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. 10625
    Prev
    Next
    INDEX
    Explanations

    phrases containing words that express positivity or admiration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express preference for something being the best or better option

    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
    naires
    -0.74
    stairs
    -0.70
    adra
    -0.69
    sembly
    -0.64
    ortment
    -0.64
    giene
    -0.64
    area
    -0.63
    hiro
    -0.60
    wash
    -0.60
    aine
    -0.59
    POSITIVE LOGITS
     than
    0.93
     testament
    0.81
     encaps
    0.80
     Than
    0.76
     succinct
    0.74
     nor
    0.72
     deserving
    0.70
     juxtap
    0.69
     exempl
    0.68
     illustration
    0.67
    Activations Density 0.114%

    No Known Activations