© 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. 10614
    Prev
    Next
    INDEX
    Explanations

    references to job positions or roles and terms related to ascending to positions of power

    oai_token-act-pair · gpt-3.5-turbo

    references to resignations and positions within organizations or government

    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
    Quality
    -0.78
    Consumer
    -0.78
    Kin
    -0.75
     Marketplace
    -0.75
    Feed
    -0.75
    products
    -0.72
    Safety
    -0.70
    ORY
    -0.68
    Area
    -0.67
    MH
    -0.67
    POSITIVE LOGITS
     appointed
    1.27
     appoint
    1.26
     appointing
    1.09
    anship
    1.03
     appointments
    0.98
     presidency
    0.97
     elected
    0.93
     presided
    0.93
     overseeing
    0.92
     successors
    0.91
    Activations Density 0.439%

    No Known Activations