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. 14706
    Prev
    Next
    INDEX
    Explanations

    keywords related to sweet foods or flavors

    oai_token-act-pair · gpt-3.5-turbo

    the word "sweet" and its variations in context

    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
    Downloadha
    -1.16
     Administ
    -0.81
    kson
    -0.80
    agall
    -0.73
    NUM
    -0.68
     Occupations
    -0.67
     ineligible
    -0.67
    ctica
    -0.66
     Aerospace
    -0.66
    agher
    -0.66
    POSITIVE LOGITS
    heart
    1.45
    eners
    1.42
    ened
    1.29
    ener
    1.24
    ening
    1.14
    bread
    1.14
     potato
    1.11
    est
    1.07
    sweet
    0.94
     potatoes
    0.94
    Activations Density 0.030%

    No Known Activations