© 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. 13523
    Prev
    Next
    INDEX
    Explanations

    time-related references in the text

    oai_token-act-pair · gpt-3.5-turbo

    various phrases indicating approximate time 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
    911
    -0.65
    alist
    -0.63
    matic
    -0.61
     Byrd
    -0.61
    anus
    -0.61
    2020
    -0.61
    smith
    -0.61
    work
    -0.61
    always
    -0.60
    protect
    -0.60
    POSITIVE LOGITS
    ugu
    0.76
    othes
    0.75
    oths
    0.71
    bered
    0.69
    =-=-=-=-
    0.67
    utra
    0.66
    ovych
    0.65
    apy
    0.65
    zin
    0.65
    rentices
    0.64
    Activations Density 0.010%

    No Known Activations