© 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. 4-RES-JB
    11. 22275
    Prev
    Next
    INDEX
    Explanations

    terms related to finance, business, and economics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economics and finance

    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
    hai
    -0.66
    hin
    -0.63
    nen
    -0.62
    ×IJ
    -0.59
    姫
    -0.57
    tsky
    -0.57
    uma
    -0.56
     sidx
    -0.56
    sov
    -0.56
     Oss
    -0.54
    POSITIVE LOGITS
     abound
    0.64
     flourished
    0.59
     pervasive
    0.53
     alike
    0.50
     permitting
    0.50
     constructs
    0.49
     DOI
    0.49
     built
    0.49
     aided
    0.49
    efficiency
    0.49
    Activations Density 2.448%

    No Known Activations