© 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 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. 14734
    Prev
    Next
    INDEX
    Explanations

    terms related to time periods, particularly focusing on intervals of months or years

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time periods or durations

    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
    risome
    -0.79
    atchewan
    -0.74
     srfAttach
    -0.71
    mbuds
    -0.71
    ulkan
    -0.70
    tools
    -0.68
     unfocusedRange
    -0.66
    psc
    -0.65
    itech
    -0.65
    ategor
    -0.65
    POSITIVE LOGITS
    imester
    1.10
    uary
    0.71
     harbour
    0.66
    anza
    0.66
     of
    0.65
    icum
    0.65
     whiff
    0.65
     Paddock
    0.64
     anniversary
    0.64
     onwards
    0.64
    Activations Density 0.127%

    No Known Activations