© 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. 8-RES-JB
    11. 6978
    Prev
    Next
    INDEX
    Explanations

    mentions of various actions and events related to receiving support or attention from others

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their contributions or impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unpop
    -0.68
    onet
    -0.68
    aucuses
    -0.67
    geries
    -0.65
    lesh
    -0.60
    maxwell
    -0.60
    dry
    -0.60
     combustion
    -0.60
    clusions
    -0.59
     incrim
    -0.58
    POSITIVE LOGITS
     afforded
    1.00
     endured
    0.93
     bestowed
    0.87
     wrought
    0.85
     faced
    0.83
     incurred
    0.75
     brought
    0.73
     accrued
    0.72
     inflicted
    0.72
     received
    0.71
    Activations Density 0.265%

    No Known Activations