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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 21056
    Prev
    Next
    INDEX
    Explanations

    phrases related to countries or nations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific country

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

    No Comments

    Negative Logits
    eport
    -0.74
    ovember
    -0.74
    ocry
    -0.70
    LEASE
    -0.69
    chel
    -0.69
    ritch
    -0.68
    inventoryQuantity
    -0.68
    ctory
    -0.67
    wcsstore
    -0.67
    sbm
    -0.67
    POSITIVE LOGITS
    wide
    1.27
    men
    0.86
    side
    0.83
     Ãľ
    0.81
    oslov
    0.80
     Albania
    0.74
     overth
    0.73
     Tunisia
    0.73
     sovere
    0.73
     illegally
    0.72
    Activations Density 0.049%

    No Known Activations