Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23817
    Prev
    Next
    INDEX
    Explanations

    mentions of pancakes and syrup

    oai_token-act-pair · gpt-3.5-turbo

    references to pancakes and syrup

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ment
    -0.86
    stra
    -0.80
    ments
    -0.79
    mint
    -0.78
    nuts
    -0.77
     Trader
    -0.76
    nut
    -0.71
    culosis
    -0.70
    chin
    -0.69
    ious
    -0.69
    POSITIVE LOGITS
     syrup
    0.93
     pancakes
    0.88
    ĸļ
    0.83
    ipedia
    0.76
    aye
    0.75
    XT
    0.75
     panc
    0.71
    akeru
    0.70
    rase
    0.70
    bsite
    0.67
    Activations Density 0.040%

    No Known Activations