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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 1096
    Prev
    Next
    INDEX
    Explanations

    cosmetic terms related to beauty products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cosmetics and beauty products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.92
    lesi
    -0.84
    OTAL
    -0.77
    SPONSORED
    -0.71
    sic
    -0.71
    IENT
    -0.70
     citation
    -0.69
    fighters
    -0.69
    hend
    -0.67
    ISTORY
    -0.66
    POSITIVE LOGITS
     coat
    1.02
     mascara
    1.00
     moistur
    0.99
     lipstick
    0.99
     coating
    0.99
     shampoo
    0.98
    mble
    0.94
     perfume
    0.94
     fragrance
    0.93
     formulations
    0.93
    Activations Density 0.137%

    No Known Activations