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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10255
    Prev
    Next
    INDEX
    Explanations

    dates expressed in the ordinal form

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of date formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbuds
    -0.64
     showc
    -0.60
    Marginal
    -0.58
     pedigree
    -0.57
    opic
    -0.57
     chancellor
    -0.56
     diam
    -0.55
     herpes
    -0.54
    HOME
    -0.53
     undis
    -0.53
    POSITIVE LOGITS
     2018
    0.93
     2017
    0.93
     2016
    0.84
     2014
    0.81
     2015
    0.80
     2013
    0.80
     2019
    0.79
    pole
    0.78
    ulhu
    0.77
    2017
    0.75
    Activations Density 0.031%

    No Known Activations