© 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. 8-RES-JB
    11. 4293
    Prev
    Next
    INDEX
    Explanations

    discount codes or promotional offers

    oai_token-act-pair · gpt-3.5-turbo

    promotional elements related to codes and discounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gd
    -0.80
    anwhile
    -0.79
    wl
    -0.78
     Bung
    -0.77
     Hastings
    -0.73
     wast
    -0.72
     sho
    -0.71
     Hearth
    -0.71
     Hamburg
    -0.69
    Glass
    -0.67
    POSITIVE LOGITS
    ptin
    0.81
     ãĢĮ
    0.76
    ribes
    0.76
     Pis
    0.75
     sidx
    0.74
    asio
    0.72
    soType
    0.72
    RIPT
    0.70
     Prediction
    0.70
    yrics
    0.69
    Activations Density 0.479%

    No Known Activations