© 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. 11-RES-JB
    11. 22351
    Prev
    Next
    INDEX
    Explanations

    phrases or abbreviations related to the abbreviation 'MS'

    oai_token-act-pair · gpt-3.5-turbo

    references to Microsoft products or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rers
    -0.75
    rer
    -0.75
    framework
    -0.71
    rette
    -0.66
     damned
    -0.65
     speaking
    -0.63
    redo
    -0.62
    rency
    -0.61
    uated
    -0.60
     midway
    -0.60
    POSITIVE LOGITS
    RP
    1.20
    NBC
    1.11
    DN
    1.09
    gt
    1.03
    DOS
    0.96
    VC
    0.95
    FT
    0.93
    Cs
    0.91
    aunders
    0.87
    Fs
    0.87
    Activations Density 0.033%

    No Known Activations