© 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. 17530
    Prev
    Next
    INDEX
    Explanations

    mentions of periods of time, particularly the word "decades"

    oai_token-act-pair · gpt-3.5-turbo

    references to long periods of time, specifically decades

    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
    amina
    -0.72
    apa
    -0.71
    Package
    -0.67
    Ability
    -0.66
    iqu
    -0.62
    uala
    -0.61
    anamo
    -0.61
    Case
    -0.60
    liction
    -0.60
    atche
    -0.60
    POSITIVE LOGITS
     ago
    1.16
    ĸļ
    0.96
     Ago
    0.95
     nostalg
    0.79
     Coffin
    0.76
     ILCS
    0.74
     millennia
    0.72
    é¾įå¥ij士
    0.72
     hindsight
    0.70
    arily
    0.70
    Activations Density 0.030%

    No Known Activations