© 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. 0-RES-JB
    11. 15640
    Prev
    Next
    INDEX
    Explanations

    words related to action or change that are in their gerund form, ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    words related to assertiveness and active participation

    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
     sax
    -0.66
     cert
    -0.61
     min
    -0.61
     dram
    -0.58
     quart
    -0.57
     mornings
    -0.57
     Unch
    -0.56
     MILL
    -0.55
     legend
    -0.55
     Knights
    -0.55
    POSITIVE LOGITS
    ive
    4.43
    ives
    2.70
    ively
    2.44
    IVE
    2.32
    ived
    2.16
    iving
    2.01
    iveness
    1.91
    IVES
    1.88
    ivity
    1.87
    ïve
    1.85
    Activations Density 0.015%

    No Known Activations