© 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. 11-RES-JB
    11. 6481
    Prev
    Next
    INDEX
    Explanations

    phrases related to the reversal or violation of laws of physics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to reversible processes in physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grim
    -0.79
    camp
    -0.79
    pit
    -0.75
    TIT
    -0.75
    podcast
    -0.73
    reth
    -0.73
    tower
    -0.72
    displayText
    -0.71
     Sang
    -0.71
    arag
    -0.70
    POSITIVE LOGITS
     quantum
    1.37
     entropy
    1.32
     invari
    1.27
     entangled
    1.21
     equilibrium
    1.18
     finite
    1.18
     Turing
    1.17
     \(\
    1.16
     \(
    1.14
     symmetry
    1.13
    Activations Density 0.432%

    No Known Activations