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. 7571
    Prev
    Next
    INDEX
    Explanations

    words related to religious freedom and religious institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to religious freedom and rights

    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
    ĸļ
    -0.79
    motion
    -0.78
     Incredible
    -0.69
     newsp
    -0.65
    hyde
    -0.65
     Toll
    -0.62
    neau
    -0.61
    catch
    -0.61
    vous
    -0.61
    vious
    -0.61
    POSITIVE LOGITS
     denominations
    0.91
     nuns
    0.85
     denomination
    0.85
     Judaism
    0.84
    Jews
    0.81
     holiest
    0.80
     sect
    0.80
     sects
    0.79
     choir
    0.78
     theology
    0.78
    Activations Density 0.419%

    No Known Activations