© 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. 1-RES-JB
    11. 20807
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of restoration or bringing something back to its former state

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "restored" and related terms suggesting the act of restoration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MAT
    -0.91
    Kids
    -0.88
    furt
    -0.76
    Drug
    -0.75
    RY
    -0.75
    EVA
    -0.75
    Die
    -0.75
    POL
    -0.73
    QB
    -0.72
    KER
    -0.72
    POSITIVE LOGITS
     restored
    1.46
     restoration
    1.38
     restore
    1.28
     restoring
    1.25
     restores
    1.25
     Restore
    0.95
     salvage
    0.92
     regeneration
    0.91
     regain
    0.87
     reinstated
    0.84
    Activations Density 0.008%

    No Known Activations