© 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. 17627
    Prev
    Next
    INDEX
    Explanations

    elements related to bringing something to life or into motion

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of bringing things to life or creating reality

    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
    anus
    -0.81
    ammy
    -0.66
    ells
    -0.64
    anche
    -0.61
    Disk
    -0.61
    yip
    -0.61
    imar
    -0.61
    oga
    -0.60
    uci
    -0.60
    arij
    -0.60
    POSITIVE LOGITS
     anew
    0.78
     via
    0.71
     electronically
    0.71
     ASAP
    0.68
    HER
    0.66
     ÙĪ
    0.65
     overnight
    0.65
     digitally
    0.65
     electr
    0.62
     faster
    0.61
    Activations Density 0.147%

    No Known Activations