© 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. 11340
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Trump" in various 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
     warp
    -0.72
     Droid
    -0.72
     Guinness
    -0.72
     Bulgarian
    -0.69
     Nordic
    -0.65
     variance
    -0.65
     Voyager
    -0.65
     cyan
    -0.64
     decomp
    -0.64
     cloak
    -0.63
    POSITIVE LOGITS
    ¬
    1.16
    £
    1.12
    ı
    1.11
    Į
    1.11
    ¹
    1.09
    ¦
    1.03
    ª
    1.02
    Ī
    1.00
    į
    1.00
    Ĵ
    0.98
    Activations Density 0.376%

    No Known Activations