© 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. 3-RES-JB
    11. 21183
    Prev
    Next
    INDEX
    Explanations

    words related to instability and unpredictability

    oai_token-act-pair · gpt-3.5-turbo

    terms related to volatility and instability in financial or economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inen
    -0.89
    ema
    -0.86
    esan
    -0.81
    cedented
    -0.80
    udeb
    -0.79
    berman
    -0.79
    ulhu
    -0.79
    ophers
    -0.77
    AME
    -0.76
    shire
    -0.76
    POSITIVE LOGITS
     volatile
    1.07
     fluctuations
    0.96
     unstable
    0.91
     combust
    0.86
     volatility
    0.84
    atile
    0.83
    atility
    0.83
     swings
    0.80
     capacitor
    0.80
     triglycer
    0.78
    Activations Density 0.007%

    No Known Activations