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. 4517
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronics and technology, particularly circuit boards and specific technological components

    oai_token-act-pair · gpt-3.5-turbo

    elements related to guiding or providing direction in various contexts

    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
    aucuses
    -0.72
    ño
    -0.69
    uba
    -0.60
    alkyrie
    -0.60
    igham
    -0.59
    ena
    -0.58
    ynes
    -0.58
    ormonal
    -0.57
    ubi
    -0.57
    inelli
    -0.56
    POSITIVE LOGITS
    rawdownloadcloneembedreportprint
    0.59
     Gleaming
    0.58
     EDITION
    0.56
     Galile
    0.54
    aten
    0.53
    Downloadha
    0.53
     Meditation
    0.53
     Revis
    0.52
     LLP
    0.52
     Marriott
    0.52
    Activations Density 1.121%

    No Known Activations