© 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. 4-RES-JB
    11. 12297
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to development teams, including tasks, collaboration, and management

    oai_token-act-pair · gpt-3.5-turbo

    references to development teams and their activities

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

    No Comments

    Negative Logits
    SPONSORED
    -0.77
    miss
    -0.75
     telev
    -0.73
    otom
    -0.72
    racial
    -0.70
    BALL
    -0.70
    NetMessage
    -0.69
    netflix
    -0.68
    drug
    -0.67
    xon
    -0.66
    POSITIVE LOGITS
     Developers
    0.99
     Documentation
    0.90
     upstream
    0.88
     developers
    0.84
     repository
    0.83
     Extensions
    0.82
     contributors
    0.81
     wiki
    0.79
     cornerstone
    0.78
     Developer
    0.77
    Activations Density 0.165%

    No Known Activations