© 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. 10673
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or impactful events or changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate causes or events resulting in significant change

    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
     Wired
    -0.66
     Straw
    -0.65
     Ammo
    -0.64
     Splash
    -0.64
     Moss
    -0.64
     Sung
    -0.63
     Ware
    -0.63
     quote
    -0.63
    ogie
    -0.61
     Hold
    -0.61
    POSITIVE LOGITS
    EStream
    0.81
    MpServer
    0.80
    Interstitial
    0.78
    strate
    0.78
    ional
    0.77
    doms
    0.76
     Seym
    0.76
    ptoms
    0.75
    ordinate
    0.72
     convol
    0.71
    Activations Density 0.031%

    No Known Activations