© 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. 3-RES-JB
    11. 1930
    Prev
    Next
    INDEX
    Explanations

    references to someone being a 'lifelong' member or fan of something

    oai_token-act-pair · gpt-3.5-turbo

    references to lifelong conditions or commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otaur
    -0.79
    tical
    -0.78
     Cosponsors
    -0.77
    gged
    -0.75
    annis
    -0.73
     Vendor
    -0.70
    dash
    -0.67
     Gemini
    -0.67
    pta
    -0.65
    SEC
    -0.65
    POSITIVE LOGITS
     lifelong
    1.03
    etheless
    0.85
    hab
    0.74
     bliss
    0.74
     dream
    0.72
    urable
    0.71
    interest
    0.71
     pleasure
    0.70
    mount
    0.67
    isable
    0.66
    Activations Density 0.014%

    No Known Activations