© 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 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. 0-RES-JB
    11. 9655
    Prev
    Next
    INDEX
    Explanations

    words related to orders or commands

    oai_token-act-pair · gpt-3.5-turbo

    the word "or" and its various contexts in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fighting
    -0.63
     speeches
    -0.62
    backer
    -0.62
     skirm
    -0.61
     ki
    -0.59
     faced
    -0.59
     idle
    -0.59
     chalk
    -0.57
     spit
    -0.57
     myself
    -0.56
    POSITIVE LOGITS
    OR
    4.05
    ORS
    2.95
    ORED
    2.21
    ORY
    2.05
    or
    1.98
    ors
    1.81
    ORE
    1.74
    ORN
    1.72
    oring
    1.51
    ORD
    1.50
    Activations Density 0.007%

    No Known Activations