Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 16048
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical or international relations

    oai_token-act-pair · gpt-3.5-turbo

    references to countries and geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pires
    -0.72
    ertodd
    -0.62
    actionDate
    -0.59
    ģĸ
    -0.58
    »Ĵ
    -0.58
    )=(
    -0.54
     [|
    -0.53
    UTERS
    -0.53
     Unloaded
    -0.53
     âĶľâĶĢâĶĢ
    -0.52
    POSITIVE LOGITS
     debacle
    0.95
     fiasco
    0.92
     controversy
    0.84
     situation
    0.84
     predicament
    0.84
     shortcomings
    0.83
     plight
    0.82
     aspect
    0.81
     incident
    0.80
     phenomenon
    0.78
    Activations Density 1.012%

    No Known Activations