© 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. 11354
    Prev
    Next
    INDEX
    Explanations

    words related to enabling or starting a process or feature

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of activation

    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
    esan
    -0.77
    cas
    -0.75
    elf
    -0.70
     Hague
    -0.68
    aco
    -0.67
    erer
    -0.66
    ×IJ
    -0.65
    yah
    -0.64
    opic
    -0.64
     Hann
    -0.63
    POSITIVE LOGITS
     activation
    1.19
     activated
    1.13
     activate
    1.02
     activ
    1.00
     activating
    0.98
     activates
    0.97
    activation
    0.93
    ividual
    0.90
     charcoal
    0.87
    activated
    0.85
    Activations Density 0.011%

    No Known Activations