© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6429
    Prev
    Next
    INDEX
    Explanations

    words related to counter-terrorism efforts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to terrorism and counter-terrorism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curve
    -0.72
     depend
    -0.68
     trusting
    -0.68
     Pike
    -0.66
     disc
    -0.66
     camp
    -0.65
     sign
    -0.65
     rod
    -0.64
     clients
    -0.64
     coil
    -0.64
    POSITIVE LOGITS
    terrorism
    3.49
    terror
    2.88
    terrorist
    2.46
    Terror
    2.17
     Terrorism
    1.75
     counterterrorism
    1.61
     terrorism
    1.41
    ISIS
    1.38
    Islam
    1.31
    piracy
    1.29
    Activations Density 0.014%

    No Known Activations