© 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. 8831
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    instances of dates or time indicators

    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
     exha
    -0.70
    arantine
    -0.67
    kef
    -0.65
    essors
    -0.65
     proble
    -0.65
    ught
    -0.63
     exploiting
    -0.62
     predec
    -0.62
     behavi
    -0.62
    keyes
    -0.61
    POSITIVE LOGITS
     2018
    1.13
     2017
    1.11
     29
    1.03
     2015
    1.03
     28
    1.02
     2014
    1.02
     2013
    1.01
     06
    1.00
     27
    0.99
     2016
    0.99
    Activations Density 0.093%

    No Known Activations