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. 11-RES-JB
    6. 8074
    Prev
    Next
    INDEX
    Explanations

    phrases related to the evolution or development of relationships or systems

    oai_token-act-pair · gpt-3.5-turbo

    relationships and dynamic interactions among entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Removal
    -0.72
    arrass
    -0.66
    judicial
    -0.65
     mentioning
    -0.65
     Attention
    -0.65
     Cruel
    -0.65
     banned
    -0.64
    calling
    -0.62
     Bans
    -0.62
     Jenny
    -0.62
    POSITIVE LOGITS
     evolve
    1.70
     flourish
    1.63
     thrive
    1.49
     evolves
    1.48
     prosper
    1.34
     emerge
    1.31
     survive
    1.30
     adapt
    1.27
     grow
    1.24
     develop
    1.23
    Activations Density 0.381%

    No Known Activations