© 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. 0-RES-JB
    11. 11549
    Prev
    Next
    INDEX
    Explanations

    text related to power sources

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of energy sources and their applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subt
    -0.83
     inward
    -0.64
     ..."
    -0.63
     int
    -0.63
     Cum
    -0.61
     photograph
    -0.60
     et
    -0.60
     alle
    -0.60
     Hib
    -0.60
     districts
    -0.60
    POSITIVE LOGITS
    powered
    4.09
     powered
    2.09
    power
    1.94
     Powered
    1.78
    powers
    1.59
    equipped
    1.43
    owered
    1.40
     powering
    1.36
    enabled
    1.26
    Power
    1.26
    Activations Density 0.013%

    No Known Activations