© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7761
    Prev
    Next
    INDEX
    Explanations

    instances where something happens despite a specific circumstance, typically going against expectations or norms

    oai_token-act-pair · gpt-3.5-turbo

    the word "despite" and its context of overcoming challenges or obstacles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vantage
    -0.83
    iem
    -0.81
    ahime
    -0.81
    venture
    -0.79
    seed
    -0.78
    asus
    -0.78
    aird
    -0.77
    isa
    -0.76
    apon
    -0.76
    enter
    -0.75
    POSITIVE LOGITS
     having
    1.08
     admitting
    0.96
     being
    0.95
     assurances
    0.95
     objections
    0.92
     warnings
    0.91
     appearances
    0.90
     acknowledging
    0.89
     setbacks
    0.88
     insisting
    0.88
    Activations Density 0.038%

    No Known Activations