© 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. 3-RES-JB
    6. 7213
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to various knitting activities and tools

    oai_token-act-pair · gpt-3.5-turbo

    terms related to knitting and crochet activities

    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
    inez
    -0.95
    enture
    -0.88
    undai
    -0.77
    resy
    -0.73
    illac
    -0.70
    ilities
    -0.70
    anamo
    -0.70
     Cheong
    -0.69
     vested
    -0.67
     Oro
    -0.66
    POSITIVE LOGITS
     yarn
    1.26
     knit
    1.22
     stitch
    1.18
     crochet
    1.15
     knitting
    1.08
    wear
    0.98
    knit
    0.97
     stitches
    0.94
     woven
    0.94
     strand
    0.86
    Activations Density 0.028%

    No Known Activations