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

    Neuronpedia

    APICircuit 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. 1451
    Prev
    Next
    INDEX
    Explanations

    words related to vitality and energy

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to the theme of being "alive."

    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
    ibrary
    -0.87
    gling
    -0.85
    icol
    -0.82
    emouth
    -0.80
    uyomi
    -0.80
    oldemort
    -0.77
    chard
    -0.76
    emic
    -0.75
    atalie
    -0.75
    acca
    -0.75
    POSITIVE LOGITS
     Zur
    0.80
     Coh
    0.79
     Jou
    0.78
     Swarm
    0.77
     Mankind
    0.74
     Ryder
    0.71
     Remastered
    0.68
     Adin
    0.68
    ECK
    0.68
    è¦ļéĨĴ
    0.67
    Activations Density 0.036%

    No Known Activations