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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 3857
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of revival or renewal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of revival or revitalization

    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
    tu
    -0.72
     Preferences
    -0.66
    obe
    -0.66
     TSA
    -0.66
    ï¸ı
    -0.64
    Wire
    -0.64
    Cho
    -0.64
     biases
    -0.64
     Mathematics
    -0.63
    Stra
    -0.62
    POSITIVE LOGITS
     revived
    3.42
     revive
    3.31
     revival
    2.63
     resurrected
    2.59
     resurrect
    2.51
     resusc
    2.28
     resurrection
    2.21
     revital
    2.00
     rebirth
    1.97
     reborn
    1.91
    Activations Density 0.031%

    No Known Activations