© 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. 21757
    Prev
    Next
    INDEX
    Explanations

    references to different timeframes in the future like "years," "months," and "weeks."

    oai_token-act-pair · gpt-3.5-turbo

    terms that refer to time periods and future projections

    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
    nered
    -0.78
    ¬¼
    -0.77
    pmwiki
    -0.71
    ¶æ
    -0.71
     deserted
    -0.66
     collusion
    -0.65
     knack
    -0.64
     Entered
    -0.63
     amb
    -0.62
     Desk
    -0.61
    POSITIVE LOGITS
     onwards
    0.92
     hereafter
    0.81
    hops
    0.79
    .<
    0.79
    rica
    0.77
    ancers
    0.76
     onward
    0.76
    antically
    0.75
    ilitating
    0.74
    2019
    0.71
    Activations Density 0.093%

    No Known Activations