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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 21462
    Prev
    Next
    INDEX
    Explanations

    historical and political terms and names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to finance and political influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selfies
    -0.90
     selfie
    -0.82
     GoPro
    -0.75
     Zika
    -0.72
     IoT
    -0.72
     emoji
    -0.72
     2017
    -0.72
     2018
    -0.70
     2016
    -0.68
     Spotify
    -0.68
    POSITIVE LOGITS
    .[
    1.25
     thereafter
    1.23
     postwar
    1.13
     until
    1.07
    later
    1.06
    ,[
    1.05
     during
    1.04
     1937
    1.01
     afterward
    1.01
     afterwards
    1.00
    Activations Density 0.910%

    No Known Activations