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. 1-RES-JB
    6. 19236
    Prev
    Next
    INDEX
    Explanations

    words related to feeding or providing nourishment

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "feed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alkyrie
    -0.75
    vu
    -0.73
    asar
    -0.69
    itars
    -0.66
     pledging
    -0.65
     LIMITED
    -0.63
     vaginal
    -0.62
    968
    -0.61
     chast
    -0.61
    aspberry
    -0.61
    POSITIVE LOGITS
    feed
    1.38
     feeds
    1.34
     feed
    1.27
     Feed
    1.22
     fed
    0.98
    Feed
    0.98
    stocks
    0.96
    parser
    0.90
    fed
    0.88
    masters
    0.84
    Activations Density 0.009%

    No Known Activations