© 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. 8-RES-JB
    11. 3320
    Prev
    Next
    INDEX
    Explanations

    action words related to selecting and clicking

    oai_token-act-pair · gpt-3.5-turbo

    commands related to user interaction with a software interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egal
    -0.65
    lycer
    -0.62
     premiere
    -0.61
    bred
    -0.59
     veiled
    -0.59
    athlon
    -0.57
     nationwide
    -0.57
     conceived
    -0.56
     riots
    -0.56
     convent
    -0.56
    POSITIVE LOGITS
     Apply
    0.85
     "<
    0.80
     Import
    0.79
     Settings
    0.79
     Create
    0.78
     Delete
    0.77
     Insert
    0.76
     Preferences
    0.76
     Activate
    0.75
     Config
    0.73
    Activations Density 0.066%

    No Known Activations