© 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. 1-RES-JB
    11. 16799
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to different countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "AfD" and related contextual elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SLI
    -0.69
     ÏĦ
    -0.67
    IDER
    -0.67
     Panic
    -0.66
    EngineDebug
    -0.65
     Chaser
    -0.64
     hazard
    -0.64
     dstg
    -0.64
     Quadro
    -0.62
     Galactic
    -0.61
    POSITIVE LOGITS
    ghan
    1.26
    rica
    1.25
    Af
    0.97
    bsite
    0.88
    iqueness
    0.87
    ctuary
    0.85
    romeda
    0.79
    ortun
    0.79
    andan
    0.78
    eworld
    0.78
    Activations Density 0.014%

    No Known Activations