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

    Neuronpedia

    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. 18057
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant historical events or milestones

    oai_token-act-pair · gpt-3.5-turbo

    terms related to historical events and drafts, particularly those involving revolutions and significant sports selections

    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
    etheless
    -0.77
     obser
    -0.77
     pestic
    -0.75
    cedented
    -0.75
     metic
    -0.68
    mode
    -0.68
    ãĤ½
    -0.67
    paren
    -0.65
    cially
    -0.65
    imeters
    -0.65
    POSITIVE LOGITS
    âĦ¢
    1.04
     Era
    1.03
     Awards
    0.94
     Supplement
    0.94
     Finals
    0.92
     Facility
    0.91
     Archive
    0.91
     Archives
    0.91
     Amendments
    0.90
     Conference
    0.90
    Activations Density 0.250%

    No Known Activations