© 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. 2988
    Prev
    Next
    INDEX
    Explanations

    proper names and dates of political figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant public figures and their actions or statements

    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
     Soy
    -0.92
     Tibetan
    -0.91
     XY
    -0.87
     Zhao
    -0.86
     Yel
    -0.85
     Peru
    -0.84
    ####
    -0.82
    xual
    -0.81
     Vaj
    -0.80
     ##
    -0.79
    POSITIVE LOGITS
     Christie
    2.11
    NJ
    2.00
     NJ
    1.99
     Newark
    1.73
     Rutgers
    1.71
     Jersey
    1.62
    Jer
    1.29
    Christ
    1.28
     Hob
    1.24
     Delaware
    1.23
    Activations Density 0.224%

    No Known Activations