© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 2694
    Prev
    Next
    INDEX
    Explanations

    specific terms related to geopolitical events and places such as countries, states, and historical events

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to specific events, places, and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.77
    iably
    -0.76
    theless
    -0.71
    bably
    -0.70
    flush
    -0.69
     compe
    -0.68
    entimes
    -0.67
    ritz
    -0.66
     disarm
    -0.66
    hap
    -0.65
    POSITIVE LOGITS
    ?,
    0.89
     ..."
    0.85
    ;;;;;;;;;;;;
    0.80
     Era
    0.74
     Vol
    0.72
     --------------------
    0.71
     Edition
    0.70
     POV
    0.70
     Changed
    0.69
     Named
    0.69
    Activations Density 0.311%

    No Known Activations