© 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. 11-RES-JB
    11. 9353
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to news articles about terrorism and political unrest

    oai_token-act-pair · gpt-3.5-turbo

    references to incidents involving conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Harbor
    -0.83
     Subcommittee
    -0.76
     Stanton
    -0.75
     darn
    -0.73
     (&
    -0.71
    Madison
    -0.70
     folks
    -0.68
    NAS
    -0.68
    [/
    -0.66
    ucky
    -0.66
    POSITIVE LOGITS
     Koran
    1.30
     Arabic
    1.30
     Ramadan
    1.29
     Kurdish
    1.29
     Islamic
    1.21
     Rohingya
    1.20
     Tunis
    1.19
     Moroccan
    1.19
     Islamist
    1.19
     Lebanese
    1.18
    Activations Density 0.698%

    No Known Activations