© 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. 0-RES-JB
    11. 8262
    Prev
    Next
    INDEX
    Explanations

    adjectives describing positive qualities or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    the word "great" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.76
    aria
    -0.69
    iary
    -0.68
    ebin
    -0.67
    ality
    -0.66
    çĶ°
    -0.65
    atel
    -0.65
    switch
    -0.65
    alties
    -0.64
    phrine
    -0.64
    POSITIVE LOGITS
     great
    3.28
    great
    2.39
     GREAT
    2.31
     terrific
    2.13
     fantastic
    2.03
     tremendous
    1.99
     wonderful
    1.95
    Great
    1.85
     fabulous
    1.83
     Great
    1.78
    Activations Density 0.037%

    No Known Activations