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. 19110
    Prev
    Next
    INDEX
    Explanations

    words related to computer interfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to user interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ucks
    -0.90
    wagen
    -0.85
    hur
    -0.75
    yd
    -0.73
    yss
    -0.72
    frey
    -0.70
    oil
    -0.70
    fam
    -0.70
    sis
    -0.70
    omore
    -0.70
    POSITIVE LOGITS
     interfaces
    1.03
     interface
    0.95
    eering
    0.83
     mund
    0.81
     Builder
    0.80
     elements
    0.80
     design
    0.79
     layout
    0.78
     designers
    0.77
     layouts
    0.76
    Activations Density 0.028%

    No Known Activations