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. 2-RES-JB
    6. 5152
    Prev
    Next
    INDEX
    Explanations

    phrases related to beauty

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "beauty" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    POR
    -0.78
    REL
    -0.73
    WD
    -0.70
    FY
    -0.67
     leash
    -0.66
     airborne
    -0.66
     stool
    -0.66
    BU
    -0.65
    MIT
    -0.64
     MIT
    -0.64
    POSITIVE LOGITS
    ifully
    1.24
    iful
    1.18
    iless
    1.08
    amental
    1.03
    ysc
    0.97
    emis
    0.96
    issance
    0.95
    beaut
    0.94
    ician
    0.92
    htaking
    0.90
    Activations Density 0.005%

    No Known Activations