Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11285
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical attacks in the context of Syria

    oai_token-act-pair · gpt-3.5-turbo

    mentions of chemical attacks and their perpetrators in the context of the Syrian conflict

    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
     friendships
    -0.83
     Trout
    -0.80
     Poker
    -0.79
    natureconservancy
    -0.75
     Ticket
    -0.73
     cryptoc
    -0.73
     Barcl
    -0.72
     Taxi
    -0.72
    reprene
    -0.70
     Macy
    -0.69
    POSITIVE LOGITS
     chlorine
    1.27
     chemical
    1.26
     Assad
    1.26
     Idlib
    1.22
     Syrian
    1.19
    Assad
    1.19
     Damascus
    1.16
     airstrike
    1.15
    Syria
    1.13
     Syrians
    1.12
    Activations Density 0.275%

    No Known Activations