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. 17895
    Prev
    Next
    INDEX
    Explanations

    references to glamour, glamorous aspects, or luxury

    oai_token-act-pair · gpt-3.5-turbo

    terms related to glamour and prestige

    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
    quartered
    -0.75
    lements
    -0.70
    peat
    -0.67
    akening
    -0.67
    square
    -0.62
     Kindle
    -0.61
    cies
    -0.60
    ñ
    -0.59
    etts
    -0.59
     subp
    -0.59
    POSITIVE LOGITS
     glam
    1.15
     glamorous
    0.86
    amera
    0.84
    rities
    0.80
     Tourism
    0.79
    illac
    0.78
    our
    0.77
    biz
    0.75
    ouri
    0.74
    ories
    0.71
    Activations Density 0.009%

    No Known Activations