© 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. 9806
    Prev
    Next
    INDEX
    Explanations

    terms related to political tensions and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to escalating disputes or conflicts between entities

    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
    cise
    -0.85
    prints
    -0.77
    sole
    -0.74
    icle
    -0.69
    Interstitial
    -0.68
    ume
    -0.67
    write
    -0.66
    icles
    -0.65
    Chance
    -0.65
     Upload
    -0.64
    POSITIVE LOGITS
     flared
    1.08
     tensions
    1.07
     tension
    0.95
     simmer
    0.93
     flare
    0.88
     surrounding
    0.85
     cooker
    0.85
     escal
    0.84
     arising
    0.82
     raging
    0.81
    Activations Density 0.090%

    No Known Activations