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. 12-RES-JB
    6. 15119
    Prev
    Next
    INDEX
    Explanations

    actions and everyday life details related to personal experiences and interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to colors and food-related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Beir
    -0.78
    abama
    -0.66
    slaught
    -0.66
     Sovere
    -0.66
    èĢħ
    -0.65
     [*]
    -0.65
     Hispan
    -0.65
     experien
    -0.65
     Deity
    -0.63
     Brut
    -0.63
    POSITIVE LOGITS
     shampoo
    1.28
     groceries
    1.25
     laundry
    1.20
     fridge
    1.18
     curtains
    1.16
     microwave
    1.15
     headphones
    1.15
     sunglasses
    1.14
     refrigerator
    1.14
     diapers
    1.13
    Activations Density 0.748%

    No Known Activations