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. 24250
    Prev
    Next
    INDEX
    Explanations

    references to different groups of people, particularly in a cultural or societal context

    oai_token-act-pair · gpt-3.5-turbo

    references to different ethnic groups and their interactions

    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
    Effective
    -0.80
    inventoryQuantity
    -0.79
    nel
    -0.77
    Accessory
    -0.74
    thumbnails
    -0.72
    Delivery
    -0.70
    ctor
    -0.66
     Heller
    -0.66
    ENTS
    -0.64
    Repe
    -0.64
    POSITIVE LOGITS
     peoples
    0.98
     civilizations
    0.93
    hell
    0.88
    agos
    0.86
     nations
    0.84
     Languages
    0.84
     cultures
    0.83
    wana
    0.83
     inhab
    0.79
     countries
    0.74
    Activations Density 0.081%

    No Known Activations