© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 18987
    Prev
    Next
    INDEX
    Explanations

    locations related to Amsterdam

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to the city of Amsterdam and its notable features

    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
    gars
    -0.73
     bolts
    -0.71
    ELY
    -0.70
     sacrifices
    -0.67
    IPS
    -0.67
     crops
    -0.66
     necessities
    -0.64
     resil
    -0.63
    inches
    -0.62
    entin
    -0.62
    POSITIVE LOGITS
    sterdam
    1.41
    ijk
    1.23
     Gaal
    1.06
     Amsterdam
    1.00
    ijn
    0.93
     Dhabi
    0.81
    stadt
    0.79
    stra
    0.78
    urden
    0.76
    alam
    0.76
    Activations Density 0.014%

    No Known Activations