© 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. 8-RES-JB
    11. 20162
    Prev
    Next
    INDEX
    Explanations

    countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    references to immigration and the related social, economic, and political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wins
    -0.60
     Nanto
    -0.59
    orts
    -0.59
     Motion
    -0.59
     Buk
    -0.59
    aneous
    -0.58
    imon
    -0.57
    iHUD
    -0.57
    Panel
    -0.56
    bart
    -0.54
    POSITIVE LOGITS
     voluntarily
    0.96
     fray
    0.94
     undet
    0.92
     illegally
    0.90
     unlawfully
    0.87
     willingly
    0.87
     prematurely
    0.87
     sooner
    0.82
     safely
    0.79
     permanently
    0.78
    Activations Density 0.341%

    No Known Activations