© 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. 6573
    Prev
    Next
    INDEX
    Explanations

    adjectives related to chaos, disorder, and instability

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of difficult or unstable situations

    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
    inctions
    -0.78
    ifles
    -0.77
    heit
    -0.77
    ften
    -0.76
    utra
    -0.76
    ulhu
    -0.75
    hib
    -0.74
    ©¶æ
    -0.74
    casters
    -0.70
    othing
    -0.70
    POSITIVE LOGITS
     relationship
    1.09
     situation
    1.04
     affair
    1.00
     adolesc
    1.00
     tenure
    0.95
     affairs
    0.94
     journey
    0.94
     relations
    0.91
     aftermath
    0.90
     Relationship
    0.89
    Activations Density 0.172%

    No Known Activations