© 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. 10-RES-JB
    11. 12226
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals in news or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events

    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
     glim
    -0.87
     beard
    -0.86
    à©
    -0.78
     samurai
    -0.77
     aur
    -0.76
     Aki
    -0.75
    ergy
    -0.75
    iHUD
    -0.75
     nasal
    -0.75
     kan
    -0.74
    POSITIVE LOGITS
     Clinton
    2.25
    Clinton
    2.24
     Clintons
    2.09
    clinton
    1.93
    Hillary
    1.87
     Hillary
    1.86
     Rodham
    1.60
    INTON
    1.59
     HRC
    1.59
     Podesta
    1.57
    Activations Density 0.376%

    No Known Activations