Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 23445
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Holland"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Holland" and its significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ï
    -0.75
    ormal
    -0.72
    tx
    -0.68
     subset
    -0.68
     fed
    -0.66
     formatted
    -0.66
    PC
    -0.66
     serial
    -0.65
     FANTASY
    -0.64
     echo
    -0.64
    POSITIVE LOGITS
     Holland
    4.02
     Amsterdam
    1.76
     Netherlands
    1.74
     Dutch
    1.51
     Belgium
    1.50
    Dutch
    1.49
     Ajax
    1.41
     Hague
    1.40
     Denmark
    1.33
     Normandy
    1.26
    Activations Density 0.009%

    No Known Activations