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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 22723
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of physical beauty

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of beauty

    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
    kson
    -0.82
    ern
    -0.81
    arbon
    -0.80
    izoph
    -0.77
    ership
    -0.74
    rez
    -0.69
    stantial
    -0.69
    renheit
    -0.68
    iability
    -0.68
    orum
    -0.68
    POSITIVE LOGITS
     pageant
    1.04
     queen
    0.77
    cean
    0.76
     contests
    0.75
     Flavoring
    0.74
     contestant
    0.72
     queens
    0.71
     potion
    0.69
    issance
    0.65
     beauty
    0.65
    Activations Density 0.019%

    No Known Activations