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. 9-RES-JB
    6. 649
    Prev
    Next
    INDEX
    Explanations

    categories of services or tools that can be associated with different fields such as technology, entertainment, healthcare, and more

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and digital solutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":"/
    -0.88
    imester
    -0.79
    gression
    -0.73
    STER
    -0.70
    ":"
    -0.69
    erity
    -0.68
    OLOG
    -0.67
    Ĥª
    -0.66
    -|
    -0.66
    ¤
    -0.66
    POSITIVE LOGITS
     etc
    2.11
    etc
    1.56
     ect
    1.19
     et
    0.93
     pestic
    0.81
     and
    0.80
    ...)
    0.76
    â̦)
    0.75
     ultraviolet
    0.74
     acupuncture
    0.72
    Activations Density 0.204%

    No Known Activations