© 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. 7-RES-JB
    11. 17903
    Prev
    Next
    INDEX
    Explanations

    economic terms related to financial problems or crises

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic issues and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocular
    -0.82
    姫
    -0.77
    Reviewer
    -0.75
    icrobial
    -0.71
    ãĤ±
    -0.70
    ITNESS
    -0.70
    SN
    -0.66
    erial
    -0.64
    GC
    -0.64
    Tal
    -0.64
    POSITIVE LOGITS
     plag
    1.05
     engulf
    0.87
     plagued
    0.84
     plague
    0.81
     cripp
    0.80
     caused
    0.78
     hysteria
    0.78
     ruining
    0.76
     blight
    0.76
     worsened
    0.75
    Activations Density 0.237%

    No Known Activations