© 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. 3291
    Prev
    Next
    INDEX
    Explanations

    short phrases summarizing or concluding statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms indicating summarization or encapsulation of ideas

    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
    arthed
    -0.63
    finder
    -0.62
    rouse
    -0.61
    seek
    -0.61
     proxies
    -0.59
    adders
    -0.59
     Judicial
    -0.58
    eties
    -0.58
    iae
    -0.57
     Committees
    -0.57
    POSITIVE LOGITS
     succinct
    1.13
     summed
    1.03
     gist
    0.82
     concise
    0.82
     summarized
    0.81
     nutshell
    0.80
     encaps
    0.78
     neatly
    0.74
     sentiments
    0.74
     summarizes
    0.74
    Activations Density 0.145%

    No Known Activations