© 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. 4-RES-JB
    11. 22313
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, particularly those indicating past occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the concept of "a long time."

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

    No Comments

    Negative Logits
    ramid
    -0.82
    otto
    -0.81
    rophic
    -0.74
    ulner
    -0.70
    uctions
    -0.69
    aleb
    -0.69
    andise
    -0.68
    irens
    -0.68
    isi
    -0.68
    andr
    -0.67
    POSITIVE LOGITS
     ago
    0.93
    duration
    0.83
    frames
    0.80
     gestation
    0.73
    keeping
    0.71
     duration
    0.71
    period
    0.70
     Bucc
    0.70
    frame
    0.68
     interval
    0.68
    Activations Density 0.020%

    No Known Activations