© 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
    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. 18726
    Prev
    Next
    INDEX
    Explanations

    phrases related to forceful or impactful actions, such as "blow," "bust," "kick," and "smash."

    oai_token-act-pair · gpt-3.5-turbo

    actions related to blowing or bursting something

    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
    immer
    -0.75
    States
    -0.74
    Impl
    -0.69
    Solution
    -0.67
    interrupted
    -0.65
    lihood
    -0.65
    anse
    -0.64
    saf
    -0.61
     fragment
    -0.61
    iaz
    -0.60
    POSITIVE LOGITS
     burgers
    0.90
     elbows
    0.86
     shit
    0.86
     noses
    0.84
     skulls
    0.83
     horns
    0.82
     heads
    0.81
     popcorn
    0.81
     necks
    0.80
     asses
    0.79
    Activations Density 0.263%

    No Known Activations