© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    phrases related to tragedies and loss

    oai_token-act-pair · gpt-3.5-turbo

    references to loss and sacrifice related to human lives

    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
    ħĭ
    -0.82
    SpaceEngineers
    -0.78
    ablishment
    -0.78
    iggurat
    -0.69
     guiActiveUnfocused
    -0.68
    ilibrium
    -0.67
    */(
    -0.66
    galitarian
    -0.66
    Union
    -0.64
    ãĤ´ãĥ³
    -0.63
    POSITIVE LOGITS
     innocent
    1.33
     tragically
    1.30
     unborn
    1.29
     senseless
    1.26
     innoc
    1.25
     lives
    1.23
     grieving
    1.19
     tragedies
    1.19
     countless
    1.08
     loved
    1.07
    Activations Density 0.641%

    No Known Activations