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. 8750
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific political figure named Duterte

    oai_token-act-pair · gpt-3.5-turbo

    references to Rodrigo Duterte

    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
    Ö¼
    -0.81
    essional
    -0.75
    OULD
    -0.71
    ãĥł
    -0.71
    PsyNetMessage
    -0.69
     Asheville
    -0.67
    mel
    -0.67
    ãĤ©
    -0.67
    OHN
    -0.66
    Greek
    -0.65
    POSITIVE LOGITS
     Duterte
    1.12
    uterte
    1.07
     Jinping
    0.98
     Rodrigo
    0.80
    mire
    0.79
    enei
    0.76
    ovich
    0.76
    istani
    0.74
    inho
    0.74
    eln
    0.74
    Activations Density 0.016%

    No Known Activations