© 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 EvalsExportsinterp-engineNEWAPI 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. 11783
    Prev
    Next
    INDEX
    Explanations

    terms related to historical events or organizations, particularly those related to railways and scientific expeditions

    oai_token-act-pair · gpt-3.5-turbo

    references to historical institutions and activities related to transportation and communication

    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
    ï¸ı
    -0.77
     Alexa
    -0.74
    Downloadha
    -0.69
    ebin
    -0.69
    ļéĨĴ
    -0.68
     GoPro
    -0.67
     Ashley
    -0.65
    itivity
    -0.65
     Xiaomi
    -0.64
     Lyft
    -0.64
    POSITIVE LOGITS
     1912
    1.07
     historian
    1.07
     historians
    0.99
     1914
    0.99
     1909
    0.97
     1939
    0.94
     1908
    0.93
     histor
    0.93
     1932
    0.93
     1910
    0.92
    Activations Density 0.633%

    No Known Activations