© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    words related to preparation or readiness

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "prep" or its variations, indicating a focus on preparation-related terms

    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
     Butterfly
    -0.72
     Millennium
    -0.65
     Roses
    -0.65
    geist
    -0.64
     Hearts
    -0.61
     Refuge
    -0.60
    dylib
    -0.59
     Orchestra
    -0.59
    soever
    -0.57
    hold
    -0.57
    POSITIVE LOGITS
    oster
    1.03
    ublic
    1.02
    regnancy
    0.95
    otent
    0.95
     prep
    0.94
    osition
    0.86
    essim
    0.86
    aired
    0.83
    Prep
    0.81
    ension
    0.81
    Activations Density 0.004%

    No Known Activations