© 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. 18532
    Prev
    Next
    INDEX
    Explanations

    instances of the word "towel."

    oai_token-act-pair · gpt-3.5-turbo

    references to towels and towel-related processes or equipment

    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
    omething
    -0.72
    eways
    -0.69
    places
    -0.69
    ERAL
    -0.65
    ippi
    -0.63
    tein
    -0.63
    oppers
    -0.63
    omal
    -0.62
    ymes
    -0.62
    raltar
    -0.61
    POSITIVE LOGITS
     towel
    1.28
     towels
    0.99
     curtain
    0.79
    robe
    0.78
     diaper
    0.76
    cloth
    0.75
     draped
    0.75
    pees
    0.75
     rack
    0.74
    visor
    0.74
    Activations Density 0.011%

    No Known Activations