© 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. 3-RES-JB
    6. 22895
    Prev
    Next
    INDEX
    Explanations

    words related to critical situations or points of change

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to critical situations or impending crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downloaded
    -0.65
    atto
    -0.65
     performed
    -0.65
     Kinnikuman
    -0.62
    è¦ļéĨĴ
    -0.62
     instituted
    -0.60
    add
    -0.60
    enne
    -0.59
    alle
    -0.59
     Sleeping
    -0.58
    POSITIVE LOGITS
     verge
    1.04
     brink
    1.01
    terness
    0.88
    manship
    0.84
    ï¸
    0.83
    wcs
    0.80
    veyard
    0.72
     therap
    0.68
    lihood
    0.66
     bluff
    0.66
    Activations Density 0.012%

    No Known Activations