© 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. 3-RES-JB
    11. 13253
    Prev
    Next
    INDEX
    Explanations

    words related to economics and societal values, particularly terms related to work, support, and recognition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to labor, benefit, and honor in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    outh
    -0.69
    士
    -0.67
    stein
    -0.65
    HOME
    -0.64
    Shot
    -0.64
     Tanz
    -0.63
     Gott
    -0.63
     VIDEOS
    -0.63
     Lieberman
    -0.63
     Olsen
    -0.63
    POSITIVE LOGITS
     analyse
    0.87
    alysed
    0.83
     Whilst
    0.81
    elaide
    0.80
     paran
    0.80
     defences
    0.79
    forth
    0.79
     programmes
    0.78
    sembly
    0.77
     Firstly
    0.75
    Activations Density 0.075%

    No Known Activations