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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 2199
    Prev
    Next
    INDEX
    Explanations

    event descriptions related to various activities or gatherings

    oai_token-act-pair · gpt-3.5-turbo

    events and activities related to health and wellness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porous
    -0.79
    itably
    -0.73
    addons
    -0.72
    ayers
    -0.67
    Desktop
    -0.67
    ĪĴ
    -0.66
    ilk
    -0.65
    yrics
    -0.64
     looph
    -0.63
    stood
    -0.63
    POSITIVE LOGITS
     session
    1.46
     ceremony
    1.38
     seminar
    1.33
    athon
    1.32
     event
    1.28
    fest
    1.24
     fundraiser
    1.23
     festival
    1.23
     celebration
    1.22
     festivities
    1.18
    Activations Density 0.416%

    No Known Activations