© 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. 12647
    Prev
    Next
    INDEX
    Explanations

    references to chaotic situations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to chaos and disorder in various contexts

    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
    onga
    -0.78
    sburgh
    -0.70
     ASA
    -0.69
    icrobial
    -0.69
    ACTED
    -0.68
    eele
    -0.65
    rahim
    -0.64
    ITED
    -0.63
    abase
    -0.63
     Cert
    -0.62
    POSITIVE LOGITS
     ensued
    1.15
     engulf
    1.05
     wrought
    1.04
     havoc
    0.96
     disorder
    0.95
     ens
    0.93
     surrounding
    0.90
     unfold
    0.87
     chaos
    0.87
     besie
    0.85
    Activations Density 0.088%

    No Known Activations