© 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. 0-RES-JB
    11. 10144
    Prev
    Next
    INDEX
    Explanations

    verbs related to recovering or restoring

    oai_token-act-pair · gpt-3.5-turbo

    terms related to regaining or reclaiming control or possession

    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
    enza
    -0.63
     Shipping
    -0.62
    biased
    -0.61
     upd
    -0.61
     Amb
    -0.61
    Amb
    -0.61
     MSG
    -0.61
    Labor
    -0.60
     Wanted
    -0.60
    ype
    -0.60
    POSITIVE LOGITS
     regain
    2.45
     reclaim
    2.36
     recapt
    2.12
     regained
    2.06
     reclaimed
    1.99
     retake
    1.98
     wrest
    1.68
     grapp
    1.61
     grappling
    1.50
     grapple
    1.48
    Activations Density 0.036%

    No Known Activations