© 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. 7-RES-JB
    11. 4368
    Prev
    Next
    INDEX
    Explanations

    dates in the format: year-month-day, along with numbers separated by spaces or symbols

    oai_token-act-pair · gpt-3.5-turbo

    dates and numerical identifiers related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inyl
    -0.76
    uca
    -0.76
    acebook
    -0.72
    avorite
    -0.70
    iaries
    -0.67
    itably
    -0.66
    kas
    -0.66
    izoph
    -0.64
    icion
    -0.64
    aughed
    -0.64
    POSITIVE LOGITS
    ths
    0.91
     partName
    0.67
    tnc
    0.66
     istg
    0.63
    iHUD
    0.63
    )=(
    0.61
     sym
    0.57
    rip
    0.57
     Kass
    0.57
     GMT
    0.56
    Activations Density 0.035%

    No Known Activations