© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9895
    Prev
    Next
    INDEX
    Explanations

    references to the country "Sri Lanka"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Sri Lanka

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holiday
    -0.79
    abet
    -0.78
    Hyper
    -0.78
    ALT
    -0.75
    hol
    -0.74
    onym
    -0.73
    notation
    -0.73
    ãĤ©
    -0.72
    laden
    -0.72
    inventory
    -0.72
    POSITIVE LOGITS
     Lanka
    1.39
     Nadu
    1.15
     Cricket
    1.03
     Pradesh
    1.00
     Lank
    0.86
     Sri
    0.85
     Indies
    0.74
     Albania
    0.73
     Lamp
    0.73
     Airways
    0.72
    Activations Density 0.005%

    No Known Activations