© 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. 2-RES-JB
    11. 8055
    Prev
    Next
    INDEX
    Explanations

    information related to current events or recent changes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "now."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zag
    -0.74
     Rolls
    -0.73
    ogi
    -0.72
    ashtra
    -0.71
    sym
    -0.70
     duplication
    -0.68
    aughed
    -0.67
    ippi
    -0.65
    psey
    -0.64
    ambo
    -0.64
    POSITIVE LOGITS
    adays
    1.52
     defunct
    0.93
    here
    0.91
     obsolete
    0.82
    abouts
    0.79
     underway
    0.77
     pregn
    0.73
     reversible
    0.73
    ©¶æ
    0.72
    nir
    0.71
    Activations Density 0.074%

    No Known Activations