© 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. 3-RES-JB
    11. 14729
    Prev
    Next
    INDEX
    Explanations

    phrases related to terrorist activities

    oai_token-act-pair · gpt-3.5-turbo

    references to terrorism and associated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.87
    )=(
    -0.83
    galitarian
    -0.80
    elf
    -0.77
    ership
    -0.73
    ðĿ
    -0.73
    shire
    -0.72
    pel
    -0.71
    endum
    -0.69
    dit
    -0.68
    POSITIVE LOGITS
     terrorist
    1.08
     terrorists
    1.02
     bombers
    0.99
     mastermind
    0.98
     bombing
    0.97
     bombings
    0.97
    terrorist
    0.95
     terrorism
    0.94
    abad
    0.91
     bomber
    0.90
    Activations Density 0.021%

    No Known Activations