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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19726
    Prev
    Next
    INDEX
    Explanations

    violent or chaotic events that are breaking out

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "erupt" in various contexts, particularly relating to conflict or sudden occurrences

    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
    ndra
    -0.86
    ammy
    -0.79
    uana
    -0.73
     Gemini
    -0.67
    este
    -0.66
    aky
    -0.64
    fo
    -0.63
    eline
    -0.63
    nda
    -0.63
     Louie
    -0.62
    POSITIVE LOGITS
     erupt
    0.96
     erupted
    0.96
    burst
    0.82
     bursting
    0.77
     eruption
    0.75
     anew
    0.73
     unlaw
    0.73
    CHAT
    0.71
    olate
    0.71
    wcs
    0.70
    Activations Density 0.011%

    No Known Activations