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. 2-RES-JB
    6. 2748
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of making or creating something

    oai_token-act-pair · gpt-3.5-turbo

    commands and references related to creation or preparation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mub
    -0.76
     Territories
    -0.75
     Territ
    -0.73
     Clause
    -0.70
     Vest
    -0.69
     Nev
    -0.67
     Patel
    -0.65
     Jordan
    -0.65
     Jed
    -0.64
    Jordan
    -0.64
    POSITIVE LOGITS
     sure
    0.90
    hift
    0.86
    chin
    0.84
    awaru
    0.83
    ampunk
    0.83
    arte
    0.82
    Maker
    0.80
    otype
    0.79
    reads
    0.77
    ogi
    0.73
    Activations Density 0.128%

    No Known Activations