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. 6993
    Prev
    Next
    INDEX
    Explanations

    words related to various types of juices

    oai_token-act-pair · gpt-3.5-turbo

    mentions of juice in various contexts

    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
     Objects
    -0.70
     Alm
    -0.70
    pers
    -0.70
     Abraham
    -0.69
    allas
    -0.69
     Osw
    -0.67
    held
    -0.65
    Decl
    -0.63
    english
    -0.63
    occup
    -0.63
    POSITIVE LOGITS
     juice
    3.70
     juices
    2.94
     Juice
    2.46
     ju
    1.60
    ju
    1.46
     vape
    1.33
    Ju
    1.31
     cider
    1.30
     soda
    1.25
     syrup
    1.23
    Activations Density 0.017%

    No Known Activations