© 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. 2-RES-JB
    11. 7754
    Prev
    Next
    INDEX
    Explanations

    references to the Summer Olympics

    oai_token-act-pair · gpt-3.5-turbo

    references to the Summer Olympics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akespe
    -0.82
    awaru
    -0.79
    uador
    -0.79
    paio
    -0.78
    ktop
    -0.78
    unal
    -0.77
    atem
    -0.77
    ourke
    -0.76
    otomy
    -0.76
    andem
    -0.75
    POSITIVE LOGITS
     Olympics
    0.91
    bugs
    0.88
     Summer
    0.87
    bug
    0.86
     Chrys
    0.85
     Winter
    0.83
    brook
    0.82
    flower
    0.81
     Veil
    0.80
     Sparkle
    0.78
    Activations Density 0.008%

    No Known Activations