© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 9025
    Prev
    Next
    INDEX
    Explanations

    words related to expenditures and actions or decisions coming to an end or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    suffixes indicating completion or results

    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
    bell
    -0.65
    ĪĴ
    -0.64
    chrom
    -0.61
    amber
    -0.58
    jar
    -0.57
     conver
    -0.55
     Cthulhu
    -0.54
     Watson
    -0.53
     Newton
    -0.53
    Tur
    -0.53
    POSITIVE LOGITS
    itures
    0.94
    inventoryQuantity
    0.87
    iture
    0.84
    staking
    0.81
     IPM
    0.79
    enza
    0.77
     Income
    0.73
    avorite
    0.71
    omics
    0.71
    folios
    0.70
    Activations Density 0.027%

    No Known Activations