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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6625
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of restoration or being restored

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "restored" and its related forms

    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
    gee
    -0.77
    stress
    -0.68
    draft
    -0.68
     Obst
    -0.66
    Drug
    -0.66
    risk
    -0.64
    orbit
    -0.61
    Der
    -0.60
    gey
    -0.59
     ide
    -0.59
    POSITIVE LOGITS
     restored
    3.89
     restoration
    2.08
     reinstated
    2.04
     preserved
    1.87
     rebuilt
    1.87
     repaired
    1.80
     regained
    1.75
     restoring
    1.74
     Restoration
    1.70
     revived
    1.66
    Activations Density 0.021%

    No Known Activations