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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23238
    Prev
    Next
    INDEX
    Explanations

    phrases related to geological locations or natural disasters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly Yellowstone and Yosemite

    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
    reen
    -0.85
    iltr
    -0.83
    reed
    -0.83
    eff
    -0.82
    edi
    -0.80
    rish
    -0.80
    aer
    -0.79
    oley
    -0.77
    uled
    -0.76
    atter
    -0.75
    POSITIVE LOGITS
     Yellowstone
    1.04
     Lodge
    1.00
     Yosemite
    0.93
     Falls
    0.87
     Niagara
    0.77
     Goose
    0.77
     XD
    0.76
     Resort
    0.75
     Springs
    0.74
     Safari
    0.74
    Activations Density 0.007%

    No Known Activations