© 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. 2-RES-JB
    11. 11997
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology or developments in various fields

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that represent the concept of currency or finance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dirt
    -0.77
    wagen
    -0.76
     shack
    -0.70
     machine
    -0.68
     bung
    -0.67
     minim
    -0.67
    itably
    -0.67
     bed
    -0.67
     pressing
    -0.67
     rooting
    -0.66
    POSITIVE LOGITS
    £
    1.11
    ¹
    1.07
    ¡
    1.01
    ¢
    0.97
    į
    0.96
    º
    0.93
    ONSORED
    0.93
    Ī
    0.91
    Dialogue
    0.90
    ł
    0.88
    Activations Density 0.623%

    No Known Activations