© 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. 14960
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical ports or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to ports 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
    matic
    -0.80
     Abortion
    -0.71
     Kelley
    -0.70
     Wichita
    -0.69
    zynski
    -0.69
     Weed
    -0.68
     Wiggins
    -0.67
    atsuki
    -0.67
     Karma
    -0.66
    animous
    -0.66
    POSITIVE LOGITS
     port
    3.75
     ports
    2.93
     Ports
    2.24
    Port
    2.08
     Port
    2.07
     ported
    1.93
    port
    1.80
    PORT
    1.58
     docks
    1.39
    ports
    1.29
    Activations Density 0.015%

    No Known Activations