© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3473
    Prev
    Next
    INDEX
    Explanations

    phrases related to business operations and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    text related to production and project management

    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
     Bundy
    -0.82
     Adolf
    -0.76
    cigarettes
    -0.73
     Rousse
    -0.72
     herself
    -0.71
     belongs
    -0.69
     mockery
    -0.66
    cair
    -0.65
     Argument
    -0.65
     Morse
    -0.64
    POSITIVE LOGITS
     ourselves
    1.06
     announce
    0.94
    catentry
    0.92
     releasing
    0.92
     publish
    0.91
     updating
    0.86
    bsite
    0.86
    onen
    0.84
     publishing
    0.83
     iter
    0.83
    Activations Density 0.357%

    No Known Activations