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. 16804
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large quantity or overwhelming presence of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to waves or floods in various contexts

    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
    ours
    -0.93
    wark
    -0.78
    orp
    -0.76
    esty
    -0.76
    bowl
    -0.74
    tw
    -0.72
    rust
    -0.71
    xtap
    -0.70
    è£
    -0.70
    minus
    -0.70
    POSITIVE LOGITS
     negativity
    1.07
     criticism
    0.99
     discontent
    0.95
     misinformation
    0.95
     lawsuits
    0.93
     activity
    0.91
     cancell
    0.89
     unwanted
    0.88
     controversy
    0.87
     unve
    0.86
    Activations Density 0.161%

    No Known Activations