© 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. 10-RES-JB
    11. 11496
    Prev
    Next
    INDEX
    Explanations

    references to organizations or entities with the term "World" in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to "World" organizations or entities, particularly health-related ones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.70
    ibility
    -0.69
     Judd
    -0.69
    »Ĵ
    -0.65
     pedals
    -0.65
     hue
    -0.65
    IBLE
    -0.64
     htt
    -0.63
     somew
    -0.63
    ibilities
    -0.62
    POSITIVE LOGITS
     Wide
    1.13
    Wide
    1.04
     Trade
    1.00
     Bank
    0.98
     Cup
    0.95
    Tour
    0.94
     Series
    0.93
    Net
    0.90
    builders
    0.89
     War
    0.88
    Activations Density 0.030%

    No Known Activations