© 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. 10-RES-JB
    11. 13639
    Prev
    Next
    INDEX
    Explanations

    time-related phrases indicating urgency or quick decision-making

    oai_token-act-pair · gpt-3.5-turbo

    terms related to time indicators or sequences, particularly focusing on the words "last" and "first."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olor
    -0.84
    apons
    -0.76
    ennes
    -0.75
    ux
    -0.75
    styles
    -0.73
    tics
    -0.73
    plays
    -0.72
    arcity
    -0.71
    raltar
    -0.70
    azard
    -0.70
    POSITIVE LOGITS
     anniversary
    0.99
     hurdle
    0.97
     minute
    0.88
     floor
    0.83
     occurrence
    0.83
     installment
    0.81
     whistle
    0.79
     day
    0.79
     iteration
    0.78
     occupant
    0.76
    Activations Density 0.104%

    No Known Activations