© 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. 10-RES-JB
    11. 10554
    Prev
    Next
    INDEX
    Explanations

    keywords related to acts of giving up something valuable for a higher purpose or cause

    oai_token-act-pair · gpt-3.5-turbo

    references to sacrifice and selflessness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ForgeModLoader
    -0.77
    DragonMagazine
    -0.71
    ogg
    -0.70
    vals
    -0.68
    lez
    -0.68
    Initialized
    -0.67
    lies
    -0.66
    rake
    -0.66
    umin
    -0.66
    track
    -0.65
    POSITIVE LOGITS
     sacrificed
    0.93
     sacrifice
    0.88
     sacrificing
    0.85
    rifice
    0.78
     sacrifices
    0.77
    ificial
    0.76
     concessions
    0.71
    olicy
    0.69
     altar
    0.66
     surrender
    0.66
    Activations Density 0.066%

    No Known Activations