© 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. 17431
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific cultural or music scenes

    oai_token-act-pair · gpt-3.5-turbo

    references to various music scenes and their dynamics

    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
    berman
    -0.89
    sburgh
    -0.83
    icrobial
    -0.79
    thood
    -0.77
    uyomi
    -0.75
    amn
    -0.75
    gements
    -0.73
    iago
    -0.71
    achev
    -0.71
    und
    -0.70
    POSITIVE LOGITS
     Scene
    0.98
     Scenes
    0.93
     scenes
    0.92
    Dialogue
    0.92
     scene
    0.85
     Veter
    0.84
    Quote
    0.79
    scene
    0.76
    osphere
    0.75
     VIDE
    0.72
    Activations Density 0.012%

    No Known Activations