© 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. 6-RES-JB
    11. 16857
    Prev
    Next
    INDEX
    Explanations

    phrases related to operations or organizations being managed or operated by someone or some entity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "run" related to operation or management

    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
    une
    -0.75
    alam
    -0.74
     Norn
    -0.65
     Ink
    -0.64
    tymology
    -0.62
     Hague
    -0.61
    ortium
    -0.61
    shapeshifter
    -0.60
     settlers
    -0.60
    ault
    -0.59
    POSITIVE LOGITS
    escape
    0.91
    running
    0.83
    ners
    0.83
    aways
    0.81
    gs
    0.81
    agate
    0.77
    corn
    0.77
    around
    0.77
    estones
    0.75
    cul
    0.73
    Activations Density 0.042%

    No Known Activations