© 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. 8-RES-JB
    11. 10143
    Prev
    Next
    INDEX
    Explanations

    references to specific time intervals like hours, days, and weeks

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to working hours and timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reth
    -0.74
    actionDate
    -0.69
    eries
    -0.68
    rities
    -0.66
    enes
    -0.64
    soType
    -0.63
    assies
    -0.63
    estern
    -0.62
    enth
    -0.61
    terness
    -0.61
    POSITIVE LOGITS
     (~
    0.83
     thereafter
    0.83
     (£
    0.71
     supplement
    0.67
     throughout
    0.66
     operating
    0.65
    [/
    0.65
     ($
    0.64
    âĪĴ
    0.64
     basis
    0.63
    Activations Density 0.075%

    No Known Activations