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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15986
    Prev
    Next
    INDEX
    Explanations

    adjectives describing actions as meaningless or unnecessary

    oai_token-act-pair · gpt-3.5-turbo

    words that denote lack of value, significance, or purpose

    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
    ortment
    -0.76
    asio
    -0.70
    erning
    -0.69
    iew
    -0.64
    ebus
    -0.64
    insula
    -0.64
    ells
    -0.63
    rosso
    -0.63
    loe
    -0.63
    oway
    -0.62
    POSITIVE LOGITS
     unless
    1.16
     except
    0.96
     compared
    0.95
     anymore
    0.93
    unless
    0.89
     anyways
    0.88
     anyway
    0.87
     until
    0.84
     whatsoever
    0.84
     owing
    0.83
    Activations Density 0.188%

    No Known Activations