© 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. 11-RES-JB
    11. 17407
    Prev
    Next
    INDEX
    Explanations

    phrases describing occurrences or actions that have been observed or reported

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "there have been."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spend
    -0.63
     Pair
    -0.59
     Deliver
    -0.57
     inflic
    -0.56
     distraction
    -0.55
    estate
    -0.55
     exerc
    -0.52
     Tycoon
    -0.52
     patronage
    -0.52
     Rite
    -0.51
    POSITIVE LOGITS
     been
    1.62
    been
    1.40
     Been
    1.17
     arisen
    1.15
     existed
    1.07
    bara
    0.94
     emerged
    0.93
     appeared
    0.89
     hitherto
    0.88
     occurred
    0.87
    Activations Density 0.055%

    No Known Activations