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. 8520
    Prev
    Next
    INDEX
    Explanations

    phrases related to the process of pasteurization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "paste" in various contexts related to food or clipboard actions

    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
    izons
    -0.70
    pires
    -0.69
    vae
    -0.68
    rians
    -0.66
    ALE
    -0.64
     Gry
    -0.64
     Targ
    -0.62
     neighboring
    -0.61
     Rebels
    -0.60
    axies
    -0.60
    POSITIVE LOGITS
     paste
    1.46
    urized
    1.35
    paste
    1.12
     Paste
    0.99
    lete
    0.92
    ur
    0.90
    ocol
    0.84
    olicy
    0.83
    ebin
    0.80
    oly
    0.80
    Activations Density 0.006%

    No Known Activations