Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13064
    Prev
    Next
    INDEX
    Explanations

    words related to specific religious and cultural events, such as "Eid" and "Ramadan"

    oai_token-act-pair · gpt-3.5-turbo

    references to Islamic holidays and religious observances, particularly Eid and Ramadan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Addiction
    -0.72
     SUP
    -0.72
     Psychiat
    -0.71
     Huntington
    -0.71
     Coastal
    -0.70
    ACP
    -0.67
     Sussex
    -0.67
     Wilmington
    -0.66
     Suite
    -0.66
     Vanderbilt
    -0.66
    POSITIVE LOGITS
     Eid
    1.21
    isoft
    1.07
    olon
    1.05
    oÄŁan
    0.92
     Ramadan
    0.88
    ophon
    0.87
    ibel
    0.87
    iday
    0.87
    gments
    0.86
    ãĥ¼ãĤ¯
    0.82
    Activations Density 0.014%

    No Known Activations