© 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. 1-RES-JB
    11. 14436
    Prev
    Next
    INDEX
    Explanations

    words related to exciting and thrilling experiences such as adventures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of adventure

    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
    uctor
    -0.85
    olen
    -0.78
    enses
    -0.77
    ensing
    -0.76
    enser
    -0.75
    early
    -0.70
    ple
    -0.69
    iths
    -0.69
    uppet
    -0.69
    plet
    -0.69
    POSITIVE LOGITS
     adventure
    1.03
     Afric
    0.92
     Adventure
    0.92
     adventures
    0.81
     Elys
    0.80
     Phant
    0.79
     awaits
    0.76
     Explorer
    0.76
    Adventure
    0.74
     Adventures
    0.73
    Activations Density 0.009%

    No Known Activations