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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1917
    Prev
    Next
    INDEX
    Explanations

    references to the news outlet "Global" with varying degrees of importance or relevance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Global," often in relation to various news and organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chers
    -0.88
    ÄŁ
    -0.87
    manship
    -0.86
    displayText
    -0.81
    ktop
    -0.80
    oÄŁ
    -0.80
    Ô
    -0.79
     âĶľ
    -0.78
    FUL
    -0.75
    chery
    -0.74
    POSITIVE LOGITS
     Witness
    0.90
    ization
    0.88
     Affairs
    0.87
     Position
    0.85
     illumination
    0.85
     warming
    0.82
     Illum
    0.82
    warming
    0.80
     Strategy
    0.78
     Responsibility
    0.77
    Activations Density 0.015%

    No Known Activations