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. 14395
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to the country Tajikistan, particularly focusing on the term "Taj"

    oai_token-act-pair · gpt-3.5-turbo

    the names of significant locations and organizations, particularly related to India and Uzbekistan

    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
     Torrent
    -0.72
    retty
    -0.67
     Arkham
    -0.66
    RAM
    -0.66
    uel
    -0.64
     Gear
    -0.63
     Angels
    -0.63
     Ventura
    -0.62
     Ubisoft
    -0.62
     Anarchy
    -0.62
    POSITIVE LOGITS
     Taj
    0.93
    merga
    0.80
    omach
    0.79
    ammu
    0.78
    istani
    0.77
    imura
    0.76
    onite
    0.74
    enei
    0.74
    osa
    0.73
    imoto
    0.72
    Activations Density 0.025%

    No Known Activations