Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19591
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology being powered by something else

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and power sources

    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
    chie
    -0.75
    sever
    -0.75
    esan
    -0.73
    edi
    -0.72
    Parents
    -0.70
     Plain
    -0.70
    nee
    -0.68
     Patriarch
    -0.66
     Neighbor
    -0.66
    arat
    -0.65
    POSITIVE LOGITS
     powered
    1.28
     powering
    1.08
     Powered
    0.93
     propelled
    0.87
     outage
    0.84
     propel
    0.83
     handc
    0.83
     wheelchair
    0.76
    undai
    0.76
     catapult
    0.75
    Activations Density 0.008%

    No Known Activations