© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7756
    Prev
    Next
    INDEX
    Explanations

    words related to fabric or cloth materials

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of fabrics and textiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MI
    -0.73
    AMI
    -0.72
    mit
    -0.71
    sets
    -0.65
    requ
    -0.63
    initions
    -0.63
    io
    -0.63
    MI
    -0.63
    IO
    -0.62
     Mandatory
    -0.62
    POSITIVE LOGITS
     cloth
    3.85
    cloth
    2.85
     linen
    1.71
     wool
    1.46
     garments
    1.42
     fabrics
    1.40
     towel
    1.38
     leather
    1.36
     fabric
    1.34
     textile
    1.33
    Activations Density 0.010%

    No Known Activations