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. 15719
    Prev
    Next
    INDEX
    Explanations

    references to tribes or tribal-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to tribal identity and related concepts

    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
    mington
    -0.78
    ————
    -0.74
    ablishment
    -0.74
    Ö¼
    -0.73
    gow
    -0.72
    ï¸
    -0.71
    OHN
    -0.71
    terday
    -0.71
    pread
    -0.70
    OPA
    -0.70
    POSITIVE LOGITS
     tribal
    0.97
     affili
    0.94
     chiefs
    0.93
     tribes
    0.85
     ancestry
    0.83
    ities
    0.83
     councils
    0.80
    istani
    0.80
     affairs
    0.79
     affiliation
    0.79
    Activations Density 0.017%

    No Known Activations