© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9219
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions happening in front of a specific audience or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases focused on events happening in front of an audience or crowd

    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
    bach
    -0.68
    pring
    -0.68
    among
    -0.67
    bush
    -0.65
    ierra
    -0.63
    isure
    -0.63
     Levels
    -0.62
    berman
    -0.62
    nell
    -0.61
    oba
    -0.61
    POSITIVE LOGITS
     cameras
    1.11
     camera
    1.04
     onlook
    0.87
     audiences
    0.87
    camera
    0.86
     Camera
    0.84
     horrified
    0.84
     fireplace
    0.84
     crowds
    0.83
     cheering
    0.83
    Activations Density 0.061%

    No Known Activations