© 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. 10-RES-JB
    11. 17454
    Prev
    Next
    INDEX
    Explanations

    specific entities, locations, and actions related to a detailed process

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with procedural elements and formal processes

    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
    ãģĦ
    -0.79
    ãĥ©ãĥ³
    -0.77
    ãĥĬ
    -0.77
    姫
    -0.77
    thumbnails
    -0.73
    ãĥĥãĥī
    -0.69
    ãĥ´
    -0.69
    inventoryQuantity
    -0.68
    gaard
    -0.67
    APTER
    -0.66
    POSITIVE LOGITS
     for
    0.69
     whereby
    0.66
    imus
    0.65
    undown
    0.65
     extraord
    0.63
    ousel
    0.63
    backs
    0.62
    enium
    0.61
    ause
    0.61
    ilitating
    0.61
    Activations Density 0.548%

    No Known Activations