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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 15218
    Prev
    Next
    INDEX
    Explanations

    references to "Hyatt" hotels or locations

    oai_token-act-pair · gpt-3.5-turbo

    the name "Hyatt" and its various forms in relation to hotels and services

    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
    mint
    -0.88
    */(
    -0.78
    tumblr
    -0.76
    ãĤ´ãĥ³
    -0.75
    éĹĺ
    -0.75
    versions
    -0.74
    ivity
    -0.73
    代
    -0.72
     Rebels
    -0.67
    ificantly
    -0.66
    POSITIVE LOGITS
     Hy
    1.12
    Hy
    1.09
    giene
    0.97
    brids
    0.88
    hy
    0.87
    undai
    0.85
    awei
    0.84
    annis
    0.76
    IGH
    0.75
    rule
    0.74
    Activations Density 0.004%

    No Known Activations