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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12366
    Prev
    Next
    INDEX
    Explanations

    references to luxury items or lifestyles

    oai_token-act-pair · gpt-3.5-turbo

    references to luxury items and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unin
    -0.88
    older
    -0.77
    nect
    -0.75
    ynthesis
    -0.72
    stant
    -0.72
    soType
    -0.71
    nen
    -0.70
    etts
    -0.69
    shi
    -0.69
    sha
    -0.68
    POSITIVE LOGITS
     luxury
    0.89
     goods
    0.88
     suites
    0.88
     accommodations
    0.86
     accommodation
    0.84
     boutique
    0.83
     apartments
    0.83
     condos
    0.82
    itton
    0.81
     hotels
    0.81
    Activations Density 0.029%

    No Known Activations