© 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. 10-RES-JB
    11. 23480
    Prev
    Next
    INDEX
    Explanations

    terms related to counterterrorism and counteractions

    oai_token-act-pair · gpt-3.5-turbo

    references to counter-terrorism concepts and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     squid
    -0.69
     sorely
    -0.69
     enclosed
    -0.66
     forgiveness
    -0.66
     laure
    -0.66
     Bees
    -0.64
     Suc
    -0.63
     PVC
    -0.63
     monog
    -0.62
     cows
    -0.62
    POSITIVE LOGITS
    intuitive
    1.48
    productive
    1.41
    claim
    1.34
    terrorism
    1.30
    argument
    1.29
    culture
    1.28
    balance
    1.27
    program
    1.25
    strike
    1.25
    counter
    1.25
    Activations Density 0.017%

    No Known Activations