Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7382
    Prev
    Next
    INDEX
    Explanations

    words related to emotional stoicism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "stoic" and its variations, indicating a focus on emotional restraint or lack of expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pathfinder
    -0.72
    URI
    -0.72
     Horizons
    -0.72
     Odyssey
    -0.68
    URR
    -0.67
     recall
    -0.67
    HCR
    -0.66
    ATA
    -0.63
    ÙĪ
    -0.63
    displayText
    -0.63
    POSITIVE LOGITS
    pper
    1.31
    ppy
    1.23
    pped
    1.20
    pping
    1.15
    ppers
    1.11
    ven
    0.96
    ops
    0.95
    uber
    0.95
    iety
    0.94
    ppings
    0.94
    Activations Density 0.018%

    No Known Activations