© 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. 10433
    Prev
    Next
    INDEX
    Explanations

    mentions of specific entities or concepts, including specific names of places, organizations, and political figures

    oai_token-act-pair · gpt-3.5-turbo

    names of businesses, organizations, or specific entities

    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
     ..."
    -0.48
    )",
    -0.47
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.45
    EStreamFrame
    -0.45
    åĤ
    -0.44
     fame
    -0.43
     laying
    -0.42
    Magikarp
    -0.42
     hers
    -0.40
     âĢ¦"
    -0.40
    POSITIVE LOGITS
    ogether
    0.59
    ortun
    0.53
    ron
    0.49
    surprisingly
    0.48
    xtap
    0.47
    News
    0.47
    yn
    0.46
    inarily
    0.46
    hetically
    0.46
    udos
    0.45
    Activations Density 1.127%

    No Known Activations