© 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. 10-RES-JB
    11. 11426
    Prev
    Next
    INDEX
    Explanations

    mentions of time frames, particularly the phrase "near future"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "near future."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥª
    -0.76
    artz
    -0.65
     Clubs
    -0.62
    ghai
    -0.60
    osterone
    -0.59
    neys
    -0.59
    Tips
    -0.58
     Disorder
    -0.58
    ubb
    -0.58
    hart
    -0.57
    POSITIVE LOGITS
    sighted
    1.29
    shore
    0.95
     misses
    0.93
    ctic
    0.91
     impossibility
    0.85
    entimes
    0.81
    future
    0.81
     limitless
    0.79
    -
    0.79
    -$
    0.77
    Activations Density 0.030%

    No Known Activations