© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 16879
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Syria" and discussions regarding military intervention in Syria

    oai_token-act-pair · gpt-3.5-turbo

    mentions of conflicts or military actions, particularly related to Syria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atin
    -0.78
    rawdownloadcloneembedreportprint
    -0.76
     newcom
    -0.75
    bery
    -0.75
     Wim
    -0.72
    haw
    -0.68
    Companies
    -0.67
    onym
    -0.66
    rious
    -0.65
    Wilson
    -0.65
    POSITIVE LOGITS
     ravaged
    0.95
     flared
    0.81
     escalated
    0.80
     illegally
    0.77
     invaded
    0.76
     unilaterally
    0.76
     rubble
    0.72
     milit
    0.72
     devastated
    0.72
     perpetrated
    0.71
    Activations Density 0.133%

    No Known Activations