© 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. 2-RES-JB
    11. 12588
    Prev
    Next
    INDEX
    Explanations

    words related to persistence or things that endure over time

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "persist" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erala
    -0.77
     GEAR
    -0.71
    neau
    -0.71
    avez
    -0.71
     GOODMAN
    -0.70
    ammy
    -0.68
    RN
    -0.68
    OME
    -0.66
     Deal
    -0.65
    foot
    -0.65
    POSITIVE LOGITS
    ently
    1.13
     persisted
    1.09
    enza
    1.04
     persist
    1.03
    ency
    0.97
     persists
    0.93
    uation
    0.80
    uously
    0.77
    uates
    0.76
     unchanged
    0.75
    Activations Density 0.006%

    No Known Activations