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. 10-RES-JB
    6. 9518
    Prev
    Next
    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web-related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThumbnailImage
    -0.73
     eleph
    -0.68
    Þ
    -0.62
     proportion
    -0.62
     bathrooms
    -0.59
     oun
    -0.59
    ortunately
    -0.58
     expulsion
    -0.58
     reluct
    -0.58
     inadequ
    -0.58
    POSITIVE LOGITS
    youtu
    0.97
    ebin
    0.90
    ctl
    0.90
    natureconservancy
    0.89
    www
    0.87
    cdn
    0.86
    youtube
    0.83
    forums
    0.83
    online
    0.82
    forum
    0.81
    Activations Density 0.012%

    No Known Activations