© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 13642
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy or sorrow

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sadness and condolences related to tragic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     endif
    -0.67
     weed
    -0.64
     fitt
    -0.63
     conquered
    -0.63
     equilibrium
    -0.62
     empires
    -0.61
    ?).
    -0.61
     manned
    -0.60
     theirs
    -0.60
     famously
    -0.59
    POSITIVE LOGITS
     saddened
    0.92
     tragic
    0.91
     senseless
    0.91
     regrett
    0.87
     irresponsible
    0.87
     allegations
    0.85
    Reports
    0.85
     circumstances
    0.83
    terday
    0.83
     unfortunate
    0.78
    Activations Density 0.311%

    No Known Activations