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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12476
    Prev
    Next
    INDEX
    Explanations

    the word "landslide"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant electoral wins or natural events referred to as "landslides."

    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
    acus
    -1.03
    illary
    -0.82
    tein
    -0.82
    endi
    -0.81
    emis
    -0.79
    ais
    -0.78
    agos
    -0.77
    ogi
    -0.76
    arians
    -0.75
    adian
    -0.73
    POSITIVE LOGITS
     landslide
    0.98
     landsl
    0.73
     Roads
    0.69
     valley
    0.67
    ãĤĭ
    0.66
     election
    0.66
    WAYS
    0.64
    cover
    0.64
    idable
    0.61
     succession
    0.61
    Activations Density 0.024%

    No Known Activations