© 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. 1-RES-JB
    11. 14574
    Prev
    Next
    INDEX
    Explanations

    the word "Rotterdam"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dam" or variations of it, often in a context related to geographical or structural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.82
     firearms
    -0.75
    yles
    -0.70
    croft
    -0.69
    Ĥª
    -0.67
     Subtle
    -0.67
     firearm
    -0.64
    lication
    -0.64
    âĢ¢âĢ¢
    -0.63
     Firearms
    -0.63
    POSITIVE LOGITS
    ukong
    1.15
    ascus
    1.02
    dam
    0.92
    abil
    0.88
    inventoryQuantity
    0.82
    heed
    0.80
    borgh
    0.79
    ned
    0.79
    ium
    0.79
    Dam
    0.79
    Activations Density 0.005%

    No Known Activations