© 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. 1-RES-JB
    11. 3913
    Prev
    Next
    INDEX
    Explanations

    words related to disorder and confusion

    oai_token-act-pair · gpt-3.5-turbo

    references to disorder or turmoil

    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
    ents
    -0.82
    arers
    -0.74
    phies
    -0.74
    ighed
    -0.73
    alties
    -0.73
    bors
    -0.73
    istle
    -0.72
    aired
    -0.71
    Personal
    -0.71
    odor
    -0.71
    POSITIVE LOGITS
     pandemonium
    1.18
     chaos
    1.12
     mayhem
    0.94
     havoc
    0.90
    cffff
    0.85
     unfold
    0.78
     ensued
    0.78
    INESS
    0.77
     redes
    0.77
     disorder
    0.76
    Activations Density 0.007%

    No Known Activations