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. 3372
    Prev
    Next
    INDEX
    Explanations

    words related to airlines

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ares."

    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
     snail
    -0.73
     DNA
    -0.66
     disinteg
    -0.66
     focus
    -0.66
     emphasis
    -0.63
     div
    -0.63
     underwater
    -0.62
     Kansas
    -0.62
     QC
    -0.61
     feedback
    -0.60
    POSITIVE LOGITS
    ares
    4.92
    ared
    2.07
    ARE
    1.98
    aring
    1.86
    are
    1.81
    arez
    1.79
    arer
    1.71
    arers
    1.33
    aires
    1.27
    ars
    1.19
    Activations Density 0.009%

    No Known Activations