© 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. 8-RES-JB
    11. 7875
    Prev
    Next
    INDEX
    Explanations

    keywords related to a person's name starting with "Vital" or "Vitality"

    oai_token-act-pair · gpt-3.5-turbo

    words associated with vitality or essential functions

    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
    ©¶æ
    -0.72
    renheit
    -0.71
    redits
    -0.71
    rame
    -0.70
    tower
    -0.65
     Meadows
    -0.65
    EEK
    -0.61
    ĵĺ
    -0.61
     Ryzen
    -0.61
    rica
    -0.60
    POSITIVE LOGITS
    ciating
    1.00
    ogy
    0.97
    istically
    0.96
    istical
    0.93
    ogical
    0.92
    ising
    0.92
    ised
    0.92
    ized
    0.91
    izing
    0.87
    istics
    0.87
    Activations Density 0.046%

    No Known Activations