© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 5064
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenging situations or crises

    oai_token-act-pair · gpt-3.5-turbo

    references to various crises and challenging situations

    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
    tein
    -0.82
    deck
    -0.80
    azines
    -0.78
    é¾
    -0.74
    alties
    -0.74
    handle
    -0.73
    parts
    -0.69
    thing
    -0.68
    gans
    -0.66
    auga
    -0.66
    POSITIVE LOGITS
     heightened
    1.23
     upheaval
    1.17
     turmoil
    1.16
     intense
    1.11
     uncertainty
    1.09
     unprecedented
    1.04
     turbulence
    1.03
     unrest
    1.03
     tumult
    1.02
     rapid
    1.01
    Activations Density 0.099%

    No Known Activations