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. 20428
    Prev
    Next
    INDEX
    Explanations

    items typically found in a makeup kit

    oai_token-act-pair · gpt-3.5-turbo

    types of clothing and cosmetic products

    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
    hement
    -1.12
    ĸļ
    -1.07
     agre
    -0.89
    ername
    -0.89
    etheless
    -0.86
    abwe
    -0.85
    nesday
    -0.80
     tremend
    -0.80
     mathemat
    -0.79
     citiz
    -0.79
    POSITIVE LOGITS
    OVA
    0.88
    References
    0.82
    Pros
    0.80
    LAN
    0.80
    Attributes
    0.80
    Posts
    0.80
    Lens
    0.79
    Instruct
    0.79
    Recommended
    0.78
    ItemThumbnailImage
    0.78
    Activations Density 0.632%

    No Known Activations