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. 22142
    Prev
    Next
    INDEX
    Explanations

    words related to the term "Mans" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or terms related to "Mans" or "mansions."

    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
    é¾įåĸļ士
    -0.73
    ties
    -0.72
    ãģĦ
    -0.69
    vernment
    -0.67
    WORK
    -0.65
    thodox
    -0.64
    >>>>>>>>
    -0.64
    berus
    -0.62
    ļéĨĴ
    -0.62
     Matrix
    -0.61
    POSITIVE LOGITS
    laughter
    1.19
    pread
    0.98
    hap
    0.90
    field
    0.86
    ouri
    0.85
    creen
    0.85
    bridge
    0.85
    mouth
    0.82
    plain
    0.82
    auga
    0.81
    Activations Density 0.018%

    No Known Activations