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. 17261
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic institutions or research organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various institutes or organizations

    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
    theless
    -1.01
     tame
    -0.71
     ages
    -0.71
     sled
    -0.70
    mere
    -0.68
    seys
    -0.68
    taboola
    -0.67
    nir
    -0.67
    =-=-=-=-=-=-=-=-
    -0.67
    catentry
    -0.66
    POSITIVE LOGITS
     Transparency
    0.78
     Square
    0.78
    una
    0.77
    itute
    0.77
    Research
    0.71
     Research
    0.71
     Institute
    0.70
    fusc
    0.70
     Institution
    0.69
     Herz
    0.68
    Activations Density 0.020%

    No Known Activations