© 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. 11-RES-JB
    11. 7672
    Prev
    Next
    INDEX
    Explanations

    comparative phrases indicating a greater degree of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express an increase or improvement in quantity or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocobo
    -0.80
    æ©
    -0.79
    https
    -0.75
    pez
    -0.72
    EStream
    -0.70
    ovie
    -0.68
    ipper
    -0.67
    bda
    -0.67
    Thumbnail
    -0.67
    ingo
    -0.66
    POSITIVE LOGITS
     they
    0.94
     you
    0.87
     likely
    0.87
     we
    0.83
     probable
    0.77
     difficult
    0.72
     accurate
    0.72
     outrageous
    0.72
     outlandish
    0.71
     comfortable
    0.70
    Activations Density 0.037%

    No Known Activations