© 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. 6-RES-JB
    11. 13468
    Prev
    Next
    INDEX
    Explanations

    time-related references, particularly mentioning specific time periods, such as years

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods, specifically relating to the last several years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ollow
    -0.74
    oola
    -0.73
    aband
    -0.69
    nel
    -0.64
    amber
    -0.64
    ancel
    -0.63
    obs
    -0.62
    iform
    -0.62
    ingen
    -0.61
    olor
    -0.61
    POSITIVE LOGITS
     decade
    1.22
     month
    1.04
     week
    1.01
     gasp
    0.96
     year
    0.94
     installment
    0.94
     millennium
    0.93
     few
    0.91
    ebin
    0.90
     century
    0.89
    Activations Density 0.038%

    No Known Activations