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. 0-RES-JB
    6. 22961
    Prev
    Next
    INDEX
    Explanations

    mentions of renewal or things being renewed

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of renewal

    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
     AI
    -0.74
    Gameplay
    -0.72
     orth
    -0.68
    Mouse
    -0.67
     Syndrome
    -0.65
     Za
    -0.64
     Tort
    -0.64
     Atari
    -0.64
     Orth
    -0.63
     HDL
    -0.62
    POSITIVE LOGITS
     renewal
    3.54
     renew
    3.47
     Renew
    2.37
     renewed
    2.35
     rejuven
    1.27
     expire
    1.26
     regeneration
    1.26
     expiration
    1.24
     reapp
    1.22
    Ren
    1.22
    Activations Density 0.021%

    No Known Activations