© 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. 1-RES-JB
    11. 23181
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent actions or incidents

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with violent and excessive actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slightest
    -0.75
    66666666
    -0.69
    croft
    -0.66
    ĪĴ
    -0.66
    faith
    -0.65
    aves
    -0.64
     Patriarch
    -0.62
    parts
    -0.61
    otes
    -0.61
    angers
    -0.59
    POSITIVE LOGITS
     spree
    1.53
     rampage
    1.01
    ãĥ¼ãĤ¯
    0.84
    ="/
    0.79
     looting
    0.77
     Hebdo
    0.73
    ãĥ¢
    0.72
    ãĥ¥
    0.71
    steen
    0.70
     Mania
    0.67
    Activations Density 0.009%

    No Known Activations