© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    phrases encouraging the reader to stay updated on various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases encouraging vigilance or attention to important information

    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
    女
    -0.77
    NetMessage
    -0.72
     tom
    -0.72
    Interstitial
    -0.68
    MpServer
    -0.67
    displayText
    -0.67
    Sov
    -0.64
     Mehran
    -0.64
    odied
    -0.62
    ody
    -0.62
    POSITIVE LOGITS
    ership
    0.85
     tabs
    0.84
    ers
    0.83
     scrolling
    0.82
     Calm
    0.80
    overs
    0.79
    s
    0.78
    watch
    0.73
    ressing
    0.72
    agh
    0.72
    Activations Density 0.022%

    No Known Activations