© 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. 4-RES-JB
    11. 10363
    Prev
    Next
    INDEX
    Explanations

    instances where caring or lack of caring is expressed regarding different subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing a lack of concern for various issues

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

    No Comments

    Negative Logits
    gallery
    -0.78
    nown
    -0.70
    EStreamFrame
    -0.70
    oda
    -0.70
    BuyableInstoreAndOnline
    -0.69
     Cosponsors
    -0.68
    redits
    -0.68
    Lay
    -0.68
    omsky
    -0.68
    ammy
    -0.67
    POSITIVE LOGITS
     preserving
    0.94
     respecting
    0.91
     whether
    0.79
     protecting
    0.77
     fairness
    0.77
     getting
    0.76
     maximizing
    0.75
     improving
    0.74
     upholding
    0.73
     optimizing
    0.73
    Activations Density 0.034%

    No Known Activations