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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 2785
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the brand "Cheerios"

    oai_token-act-pair · gpt-3.5-turbo

    word endings, particularly those associated with various forms and plurals

    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
    ãĤ´
    -0.84
    ICES
    -0.74
    $$$$
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.72
    ãĤ¤ãĥĪ
    -0.71
     Amend
    -0.70
    ãĥĩ
    -0.69
    EGIN
    -0.67
    ãĤ®
    -0.66
    MENTS
    -0.65
    POSITIVE LOGITS
    ghan
    0.86
    kee
    0.80
    ebus
    0.76
    ldon
    0.75
    vern
    0.73
    zy
    0.73
    eworthy
    0.73
    zers
    0.72
    zzo
    0.70
    zel
    0.70
    Activations Density 0.115%

    No Known Activations