© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13553
    Prev
    Next
    INDEX
    Explanations

    references to literal or metaphorical fabric

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "fabric," particularly in metaphorical or societal contexts

    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
    akedown
    -0.75
    /+
    -0.69
    rase
    -0.68
     Ludwig
    -0.66
    rank
    -0.65
    erence
    -0.64
    ares
    -0.63
    hare
    -0.63
     preceded
    -0.62
     Rank
    -0.62
    POSITIVE LOGITS
     fabric
    3.86
     fabrics
    2.28
     Fabric
    2.27
     fabrication
    1.78
    fab
    1.64
     fabricated
    1.43
     garment
    1.41
     stitching
    1.38
     cloth
    1.37
     weave
    1.30
    Activations Density 0.011%

    No Known Activations