© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 5268
    Prev
    Next
    INDEX
    Explanations

    time-related phrases like "within a couple of decades", "within a few hours drive", and "within 20 days"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating timeframes or durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uncond
    -0.69
     dearly
    -0.63
     imbalance
    -0.62
     hated
    -0.57
    ramid
    -0.57
     goodbye
    -0.55
    idon
    -0.55
    ffen
    -0.55
     superiority
    -0.55
     Difference
    -0.54
    POSITIVE LOGITS
     milliseconds
    0.97
     seconds
    0.94
     weeks
    0.90
     minutes
    0.89
     hrs
    0.87
    paces
    0.85
     hours
    0.84
    hours
    0.84
    seconds
    0.81
    cms
    0.79
    Activations Density 0.104%

    No Known Activations