© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 12215
    Prev
    Next
    INDEX
    Explanations

    phrases related to featuring or highlighting something in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to content that includes "featuring" various subjects or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calculations
    -0.70
    yden
    -0.66
    olate
    -0.65
     indirect
    -0.62
     calculation
    -0.61
    Lear
    -0.60
     mischief
    -0.59
     discipline
    -0.57
    untarily
    -0.56
    rawdownloadcloneembedreportprint
    -0.56
    POSITIVE LOGITS
     featuring
    3.22
     Featuring
    2.24
     showcasing
    2.03
     depicting
    1.95
     starring
    1.86
    feat
    1.85
    eaturing
    1.70
     featured
    1.64
     consisting
    1.59
     incorporating
    1.46
    Activations Density 0.021%

    No Known Activations