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. 0-RES-JB
    6. 14202
    Prev
    Next
    INDEX
    Explanations

    words related to the spice "cumin"

    oai_token-act-pair · gpt-3.5-turbo

    references to curcumin and its effects or applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gerry
    -0.66
     fantasy
    -0.65
     sandbox
    -0.63
     compromise
    -0.61
     playground
    -0.61
     dynasty
    -0.60
     boat
    -0.60
     College
    -0.60
     SUP
    -0.60
     party
    -0.59
    POSITIVE LOGITS
    umin
    4.76
    umen
    1.79
    umi
    1.48
    uminati
    1.23
    ilantro
    1.18
    ume
    1.13
    abal
    1.12
    umn
    1.05
     Lumin
    1.05
    umes
    1.02
    Activations Density 0.017%

    No Known Activations