© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 12544
    Prev
    Next
    INDEX
    Explanations

    numbers and monetary values

    oai_token-act-pair · gpt-3.5-turbo

    references to money and gambling contexts

    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
    ":["
    -0.71
     Marketplace
    -0.67
    isks
    -0.64
    ":[{"
    -0.61
    sites
    -0.60
    ï¸ı
    -0.60
     âĢº
    -0.60
     NETWORK
    -0.58
    ggle
    -0.58
    odcast
    -0.57
    POSITIVE LOGITS
     fame
    0.93
     himself
    0.89
    çĶ°
    0.77
     herself
    0.73
     unsuccessfully
    0.71
     stint
    0.70
    æµ
    0.65
     Himself
    0.64
     fian
    0.64
    ukemia
    0.64
    Activations Density 1.580%

    No Known Activations