© 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. 13585
    Prev
    Next
    INDEX
    Explanations

    health-related terms and behaviors, such as exercise, metabolic effects, and chemical treatments

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to awareness and vigilance

    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
    iani
    -0.69
    profits
    -0.68
    ãĥĬ
    -0.68
    yan
    -0.65
     voic
    -0.65
    spons
    -0.64
    finder
    -0.64
     turnaround
    -0.64
     entit
    -0.64
     recommendation
    -0.62
    POSITIVE LOGITS
     inh
    0.91
     overe
    0.86
     exposed
    0.85
     subjected
    0.82
     switched
    0.81
     artificially
    0.80
     improperly
    0.80
     repeated
    0.79
     concentrated
    0.78
     untreated
    0.77
    Activations Density 0.293%

    No Known Activations