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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 19150
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations, particularly airstrikes and combat activities in Syria and Iraq

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and conjunctions indicating military actions and operations in specific regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.81
    ourney
    -0.78
    advertisement
    -0.77
    awei
    -0.73
    NVIDIA
    -0.66
    ÃŃs
    -0.65
    onica
    -0.64
    Continue
    -0.63
    ugu
    -0.63
    innie
    -0.62
    POSITIVE LOGITS
     Syria
    1.32
     Afghanistan
    1.27
     Iraq
    1.26
     Yemen
    1.18
     Libya
    1.13
     eastern
    1.12
     Somalia
    1.08
     neighboring
    1.02
     northern
    1.00
     Bosnia
    1.00
    Activations Density 0.163%

    No Known Activations