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. 10597
    Prev
    Next
    INDEX
    Explanations

    references to clerics and religious leaders, particularly in the context of Shia Islam

    oai_token-act-pair · gpt-3.5-turbo

    references to clerics and leaders in a religious or political context

    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
     Packers
    -0.81
     Hitch
    -0.77
     Hawth
    -0.76
     Rover
    -0.76
     Yards
    -0.75
     Pegasus
    -0.74
     Detect
    -0.73
     Galaxy
    -0.73
     Oregon
    -0.73
     Dock
    -0.73
    POSITIVE LOGITS
     clerics
    0.95
    istani
    0.93
    onite
    0.89
     dictatorship
    0.88
     cleric
    0.87
     Hussein
    0.85
    astically
    0.84
    habi
    0.83
    doms
    0.83
    ollah
    0.83
    Activations Density 0.053%

    No Known Activations