© 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. 373
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs related to persistence or determination

    oai_token-act-pair · gpt-3.5-turbo

    adjectives describing persistence or obstinacy, particularly "stubborn"

    oai_token-act-pair · gpt-4-turbo

    terms that express persistence or stubbornness

    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
    utra
    -0.89
    ramid
    -0.89
    ographies
    -0.88
    isites
    -0.88
    imester
    -0.85
    APH
    -0.84
    ammy
    -0.83
    nesota
    -0.81
    onym
    -0.80
    owler
    -0.79
    POSITIVE LOGITS
     stubborn
    1.10
    ly
    1.03
    ness
    0.97
    nesses
    0.96
     persistence
    0.83
     streak
    0.78
     clinging
    0.78
     persever
    0.76
     steadfast
    0.76
     relent
    0.72
    Activations Density 0.022%

    No Known Activations