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. 15829
    Prev
    Next
    INDEX
    Explanations

    words related to embedded systems

    oai_token-act-pair · gpt-3.5-turbo

    references to embedded systems or the concept of embedding in various contexts

    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
    Ń·
    -0.84
    §
    -0.81
    veyard
    -0.78
    İ
    -0.77
    ãĥ£
    -0.76
     Sabha
    -0.73
    boat
    -0.70
    ãĥ¥
    -0.68
    thur
    -0.67
    hma
    -0.66
    POSITIVE LOGITS
    ding
    1.03
     embedded
    1.01
    ded
    0.92
    edded
    0.92
    rained
    0.81
    iated
    0.80
    ible
    0.79
     embed
    0.76
    tion
    0.75
    iating
    0.75
    Activations Density 0.043%

    No Known Activations