© 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. 5790
    Prev
    Next
    INDEX
    Explanations

    verbs related to leveling or leveling-related terminology

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "level" and phrases related to leveling or equalizing

    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
    enegger
    -0.80
     Sidd
    -0.74
    ROM
    -0.72
    ãĥĩ
    -0.69
     Experimental
    -0.63
     Ralph
    -0.63
     Ultr
    -0.61
    áµ
    -0.61
    politics
    -0.61
    natureconservancy
    -0.61
    POSITIVE LOGITS
     leve
    1.48
     leveled
    1.42
    lling
    1.18
    lled
    1.14
     leveling
    0.89
    aton
    0.84
    ldom
    0.80
    ldon
    0.80
    ovie
    0.75
    charges
    0.75
    Activations Density 0.013%

    No Known Activations