© 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. 9-RES-JB
    11. 15796
    Prev
    Next
    INDEX
    Explanations

    time-related phrases, specifically mentioning durations

    oai_token-act-pair · gpt-3.5-turbo

    references to durations of time, specifically weeks and days

    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
    blers
    -0.70
    illions
    -0.69
    asso
    -0.66
    agons
    -0.66
    ernels
    -0.65
    adem
    -0.62
    atically
    -0.62
    aders
    -0.62
    roth
    -0.61
    rats
    -0.61
    POSITIVE LOGITS
     stint
    1.01
     ordeal
    0.99
     hiatus
    0.98
     journey
    0.94
     moratorium
    0.88
     siege
    0.85
     span
    0.84
     regimen
    0.84
     period
    0.84
     interim
    0.84
    Activations Density 0.066%

    No Known Activations