© 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. 9-RES-JB
    11. 16570
    Prev
    Next
    INDEX
    Explanations

    terms related to counter-terrorism

    oai_token-act-pair · gpt-3.5-turbo

    terms related to counter-terrorism and its implementation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sorely
    -0.69
     laure
    -0.69
     monog
    -0.69
     Silent
    -0.65
     Indigo
    -0.63
     Limits
    -0.62
     PVC
    -0.62
     Cotton
    -0.62
     Shoals
    -0.62
     enclosed
    -0.61
    POSITIVE LOGITS
    intuitive
    1.27
    strike
    1.22
    terrorism
    1.20
    measures
    1.20
    intelligence
    1.18
    matter
    1.16
    culture
    1.15
    productive
    1.12
    attack
    1.11
    program
    1.10
    Activations Density 0.034%

    No Known Activations