© 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. 12676
    Prev
    Next
    INDEX
    Explanations

    instances where the text refers to a range or period of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "span" or duration of 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
    ysis
    -0.85
    tical
    -0.73
    ainment
    -0.70
    romeda
    -0.70
    phis
    -0.69
    tarians
    -0.67
    eers
    -0.66
    oyal
    -0.66
    sie
    -0.63
    ogical
    -0.63
    POSITIVE LOGITS
    ning
    1.04
    ner
    0.91
    ners
    0.86
    span
    0.85
    ming
    0.80
    stocks
    0.80
     span
    0.78
    ider
    0.77
     Span
    0.76
     spanning
    0.76
    Activations Density 0.030%

    No Known Activations