© 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. 22675
    Prev
    Next
    INDEX
    Explanations

    information related to time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or events that happen later in a narrative

    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
    currently
    -0.68
    formance
    -0.67
    uni
    -0.67
    afety
    -0.66
    yet
    -0.66
     currently
    -0.66
    oplan
    -0.63
    minimum
    -0.62
    ingen
    -0.60
     Prediction
    -0.60
    POSITIVE LOGITS
     recons
    0.82
     regretted
    0.79
     forg
    0.70
     realise
    0.68
     resur
    0.67
    xes
    0.66
     refin
    0.66
     rede
    0.64
     regret
    0.63
    arsity
    0.62
    Activations Density 0.203%

    No Known Activations