© 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 EvalsExportsinterp-engineNEWAPI 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. 18753
    Prev
    Next
    INDEX
    Explanations

    years or time-related references

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific years

    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
     behavi
    -0.79
    Beh
    -0.78
     guiActiveUn
    -0.61
    NetMessage
    -0.60
    ierrez
    -0.59
     advis
    -0.59
    ¿½
    -0.59
     Palestin
    -0.59
     externalToEVAOnly
    -0.59
     defe
    -0.58
    POSITIVE LOGITS
    book
    1.18
    books
    1.11
     2000
    1.04
    nings
    0.99
    long
    0.97
     2030
    0.95
     2020
    0.93
    ning
    0.89
     1914
    0.88
     2025
    0.88
    Activations Density 0.058%

    No Known Activations