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

    Neuronpedia

    Jacobian LensNEW
    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. 3831
    Prev
    Next
    INDEX
    Explanations

    financial and quantitative information, such as percentages, margins, and specific numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistical values

    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
    •Prediction Features Layer 8 GPT2 Small

    No Comments

    Negative Logits
    oris
    -0.67
    NetMessage
    -0.63
    hett
    -0.61
    ollo
    -0.60
     Dish
    -0.60
     Dialogue
    -0.58
    ãĤ¹ãĥĪ
    -0.58
    oran
    -0.57
    ador
    -0.57
    ensus
    -0.56
    POSITIVE LOGITS
     25
    1.08
     35
    1.08
     0
    1.08
     10
    1.07
     20
    1.07
     15
    1.06
     750
    1.05
     30
    1.05
     300
    1.04
     36
    1.04
    Activations Density 0.830%

    No Known Activations