© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 17260
    Prev
    Next
    INDEX
    Explanations

    words related to the impact of events or decisions on various aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to events or situations that have a significant effect or influence on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quarrel
    -0.87
     usual
    -0.78
     pecul
    -0.76
     reply
    -0.76
     barb
    -0.75
     aston
    -0.74
     ^
    -0.74
    uner
    -0.71
     pupils
    -0.71
     cant
    -0.71
    POSITIVE LOGITS
     impacted
    1.36
     foundational
    1.27
     millennials
    1.25
     initiatives
    1.23
     stakeholders
    1.21
     transformative
    1.21
     proactive
    1.19
     transitioned
    1.13
     impacting
    1.09
     leveraging
    1.08
    Activations Density 0.131%

    No Known Activations