© 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. 19265
    Prev
    Next
    INDEX
    Explanations

    the beginnings of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the beginning of events or stories

    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
    nor
    -0.65
     congratulated
    -0.64
    wa
    -0.64
    cedented
    -0.63
    ib
    -0.63
    phe
    -0.62
    hold
    -0.61
     refresh
    -0.60
    orth
    -0.60
    wd
    -0.59
    POSITIVE LOGITS
     innoc
    0.89
    WithNo
    0.79
     genesis
    0.77
    actionDate
    0.76
     anew
    0.74
    Ò
    0.73
     misunder
    0.72
     abruptly
    0.71
    Magikarp
    0.70
     spontaneously
    0.70
    Activations Density 0.088%

    No Known Activations