© 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. 10-RES-JB
    11. 18514
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to restoring and maintaining order or balance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to restoration and recovery processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atu
    -0.81
    kson
    -0.75
    iri
    -0.72
    owler
    -0.71
    gom
    -0.69
    erie
    -0.69
    annon
    -0.65
    oS
    -0.64
    Plot
    -0.63
    kers
    -0.62
    POSITIVE LOGITS
     sanity
    1.10
     composure
    1.04
     equilibrium
    0.99
     balance
    0.91
     calm
    0.88
     dignity
    0.88
     harmony
    0.86
     confidence
    0.85
     vig
    0.84
     rightful
    0.83
    Activations Density 0.081%

    No Known Activations