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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 4601
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent or intense conflicts and confrontations

    oai_token-act-pair · gpt-3.5-turbo

    incidents of conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.72
     Parables
    -0.64
    avering
    -0.63
    ãĥ¼ãĥ³
    -0.62
     reference
    -0.60
    lean
    -0.59
    onut
    -0.58
    uxe
    -0.57
     sample
    -0.57
    tiny
    -0.56
    POSITIVE LOGITS
     anew
    0.92
     spontaneously
    0.77
     concurrently
    0.77
     rife
    0.77
     engulf
    0.75
     whereby
    0.74
     intermitt
    0.73
     erupt
    0.72
     havoc
    0.69
     explos
    0.69
    Activations Density 0.191%

    No Known Activations