© 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. 20479
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disappearance or absence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gone" and its variations, indicating absence or loss

    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
    emate
    -0.62
    advertisement
    -0.61
    inus
    -0.61
    rel
    -0.60
    role
    -0.60
    eering
    -0.58
     Deity
    -0.58
    ellation
    -0.58
    FIG
    -0.56
    step
    -0.56
    POSITIVE LOGITS
     forever
    0.94
     overboard
    0.85
     unnoticed
    0.84
     bye
    0.78
     limp
    0.78
     viral
    0.78
     slack
    0.76
     rogue
    0.76
     feral
    0.75
     stale
    0.72
    Activations Density 0.042%

    No Known Activations