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. 20291
    Prev
    Next
    INDEX
    Explanations

    instances of the word "they" followed by various actions or characteristics of the individuals referred to

    oai_token-act-pair · gpt-3.5-turbo

    information related to underestimation or failure in achieving goals

    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
    emale
    -0.81
    itaire
    -0.68
     Seym
    -0.65
    icter
    -0.61
     Vaugh
    -0.61
     destro
    -0.57
     Moroc
    -0.57
     referen
    -0.55
     thous
    -0.55
    nesday
    -0.54
    POSITIVE LOGITS
     largeDownload
    0.61
     JUSTICE
    0.51
    zbollah
    0.49
     Shin
    0.49
     unders
    0.49
    mos
    0.48
     Guardians
    0.48
     hurt
    0.47
    \":
    0.46
    CVE
    0.46
    Activations Density 1.311%

    No Known Activations