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. 14435
    Prev
    Next
    INDEX
    Explanations

    references to universities, colleges, and academic institutions

    oai_token-act-pair · gpt-3.5-turbo

    HTML or coding elements related to a webpage structure

    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
    strous
    -0.58
     spoil
    -0.52
    otaur
    -0.52
     gobl
    -0.51
    maxwell
    -0.51
    eno
    -0.51
    infeld
    -0.50
    owler
    -0.49
     raw
    -0.48
    phia
    -0.48
    POSITIVE LOGITS
    iHUD
    0.64
    Dialogue
    0.56
     Kodi
    0.48
    ttle
    0.47
    uties
    0.46
    SPONSORED
    0.46
    eele
    0.45
    ALSE
    0.44
     POV
    0.44
    selected
    0.44
    Activations Density 2.049%

    No Known Activations