© 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. 2977
    Prev
    Next
    INDEX
    Explanations

    descriptions of intense emotional or physical conflicts

    oai_token-act-pair · gpt-3.5-turbo

    situations involving conflict or aggression

    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
    20439
    -0.87
    osate
    -0.73
     Consortium
    -0.69
    izen
    -0.69
    ographies
    -0.68
     administrations
    -0.67
     immortality
    -0.66
    izons
    -0.65
    inction
    -0.65
    natureconservancy
    -0.64
    POSITIVE LOGITS
     yelling
    1.12
     altercation
    1.05
     violently
    0.97
     agitated
    0.95
     shouting
    0.95
     disorderly
    0.93
     angrily
    0.93
     verbally
    0.93
     prompting
    0.90
     ensued
    0.89
    Activations Density 0.278%

    No Known Activations