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. 8-RES-JB
    6. 23146
    Prev
    Next
    INDEX
    Explanations

    keywords related to various types of "systems."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to computer systems and technology

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atorium
    -0.95
    liest
    -0.89
    bow
    -0.88
    STER
    -0.79
    ished
    -0.77
    ovich
    -0.76
    hest
    -0.75
    tein
    -0.74
    iversary
    -0.73
    naire
    -0.73
    POSITIVE LOGITS
     architectures
    1.19
    afety
    1.09
    etting
    1.06
     systems
    1.01
     engineering
    1.01
     integ
    0.96
    pace
    0.90
     architecture
    0.88
     integration
    0.85
    hare
    0.85
    Activations Density 0.094%

    No Known Activations