© 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. 13743
    Prev
    Next
    INDEX
    Explanations

    specific names, job titles, and institutions related to finance and government

    oai_token-act-pair · gpt-3.5-turbo

    key figures and roles in historical contexts

    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
     GoPro
    -0.89
    CNN
    -0.84
     emoji
    -0.82
     Zika
    -0.80
     2017
    -0.79
     selfie
    -0.78
     takeaway
    -0.76
     Netflix
    -0.76
    ï¸ı
    -0.75
     Snapchat
    -0.74
    POSITIVE LOGITS
    ,[
    1.16
    .[
    1.13
     1909
    1.06
     1932
    1.05
     postwar
    1.03
     1939
    1.03
     1936
    1.02
     1908
    1.02
    ).[
    1.01
     1907
    1.01
    Activations Density 0.746%

    No Known Activations