© 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. 11-RES-JB
    11. 338
    Prev
    Next
    INDEX
    Explanations

    references to specific time points, particularly at the end of a period

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NESS
    -0.73
    uph
    -0.69
    Connector
    -0.66
    isters
    -0.61
    liness
    -0.61
    STER
    -0.61
    ister
    -0.61
    STON
    -0.60
    utes
    -0.59
    uay
    -0.59
    POSITIVE LOGITS
     least
    1.20
     intervals
    0.99
     midnight
    0.92
     some
    0.91
    onement
    0.87
     sometime
    0.86
     runtime
    0.86
     anytime
    0.82
     length
    0.81
     noon
    0.80
    Activations Density 0.109%

    No Known Activations