© 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. 7-RES-JB
    6. 23904
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to offers and services

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to subscription offers and promotional content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.91
    ËĪ
    -0.82
    neapolis
    -0.75
    abal
    -0.75
    owicz
    -0.73
    zl
    -0.73
    umbai
    -0.72
    gger
    -0.66
     Painter
    -0.66
    esm
    -0.65
    POSITIVE LOGITS
     giveaways
    0.93
     promotions
    0.74
     occasional
    0.73
     warranties
    0.71
     restores
    0.69
     strawberries
    0.65
    osion
    0.64
     goodies
    0.63
     heals
    0.62
     aggregation
    0.62
    Activations Density 0.043%

    No Known Activations