© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24260
    Prev
    Next
    INDEX
    Explanations

    phrases related to efficiency and coordination in processes or activities

    oai_token-act-pair · gpt-3.5-turbo

    themes related to organizational efficiency and collaboration

    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
    death
    -0.72
    å¦
    -0.70
    Strange
    -0.70
     Murder
    -0.69
     hated
    -0.68
     cursed
    -0.68
     condem
    -0.66
     Mour
    -0.66
     mysteriously
    -0.65
     traitor
    -0.64
    POSITIVE LOGITS
     interoper
    1.05
     environments
    1.05
     capabilities
    1.01
     workflow
    1.00
     architectures
    0.98
     outcomes
    0.97
     opportunities
    0.96
     sustainable
    0.96
     technologies
    0.94
     excellence
    0.93
    Activations Density 1.439%

    No Known Activations