© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16834
    Prev
    Next
    INDEX
    Explanations

    words related to a decrease or decline in various metrics like prices, indexes, rates, and numbers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to decreases or declines in various contexts, particularly economic indicators

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

    No Comments

    Negative Logits
    TN
    -0.76
     License
    -0.72
     Ultra
    -0.65
    NRS
    -0.65
     Ta
    -0.65
     subpoen
    -0.64
    Sources
    -0.64
    ULT
    -0.63
    VO
    -0.63
     Allaah
    -0.63
    POSITIVE LOGITS
    luster
    0.91
    graded
    0.88
    rated
    0.83
    bush
    0.81
    downs
    0.78
    icho
    0.78
    ename
    0.77
    grading
    0.77
    winter
    0.76
    unders
    0.76
    Activations Density 0.042%

    No Known Activations