© 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. 2-RES-JB
    11. 8959
    Prev
    Next
    INDEX
    Explanations

    words or phrases that are positively related to exceptional ability or quality

    oai_token-act-pair · gpt-3.5-turbo

    the word "brilliant" in various contexts of praise and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VR
    -0.78
    asta
    -0.73
    ratom
    -0.71
    VI
    -0.70
    ople
    -0.70
    aver
    -0.70
    Demand
    -0.69
    BD
    -0.69
    PU
    -0.69
    avis
    -0.68
    POSITIVE LOGITS
     brilliance
    0.93
     brilliant
    0.92
     Brilliant
    0.84
    ulously
    0.82
    NESS
    0.79
     genius
    0.75
     barr
    0.73
     colours
    0.72
     brill
    0.72
     enough
    0.70
    Activations Density 0.007%

    No Known Activations