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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 901
    Prev
    Next
    INDEX
    Explanations

    words beginning with the fragment "sto"

    oai_token-act-pair · gpt-4-turbo

    phrases related to stoicism

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to stoicism and stoic behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urate
    -0.79
    ually
    -0.79
     Pathfinder
    -0.74
     Horizons
    -0.72
     Rend
    -0.72
     Austral
    -0.69
    HCR
    -0.68
     Triangle
    -0.67
     PubMed
    -0.67
     Odyssey
    -0.66
    POSITIVE LOGITS
     sto
    1.16
    pper
    0.99
    ppy
    0.94
    ppers
    0.88
    pped
    0.86
    pping
    0.79
    ppings
    0.79
    ops
    0.78
    uber
    0.78
    ffer
    0.77
    Activations Density 0.005%

    No Known Activations