Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4662
    Prev
    Next
    INDEX
    Explanations

    words related to knitting and "vibes"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to knitting and its associated social and creative aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enture
    -0.78
    ption
    -0.74
    perture
    -0.71
    IBLE
    -0.68
    urdue
    -0.67
    quished
    -0.67
    ovies
    -0.66
    ruciating
    -0.64
    iso
    -0.64
     dumps
    -0.60
    POSITIVE LOGITS
    knit
    1.42
     knit
    1.03
    wear
    0.89
    ters
    0.89
    erg
    0.84
    appa
    0.77
    sheet
    0.76
    lihood
    0.75
    lining
    0.74
    liners
    0.73
    Activations Density 0.023%

    No Known Activations