© 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. 2-RES-JB
    11. 3900
    Prev
    Next
    INDEX
    Explanations

    phrases related to extremist militants or terrorist groups

    oai_token-act-pair · gpt-3.5-turbo

    references to militant groups and their activities

    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
    MW
    -0.72
     Spot
    -0.70
     Gund
    -0.65
     Tycoon
    -0.65
    nder
    -0.64
     Lakes
    -0.64
     Balance
    -0.64
    upon
    -0.63
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.63
    othy
    -0.63
    POSITIVE LOGITS
     militants
    0.90
    ervatives
    0.88
     Islamists
    0.88
     gunmen
    0.87
    ervative
    0.85
     insurgents
    0.85
     gunman
    0.83
    Enlarge
    0.83
     Islamist
    0.80
     insurgency
    0.80
    Activations Density 0.017%

    No Known Activations