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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 7468
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparative phrases

    oai_token-act-pair · gpt-3.5-turbo

    superlative phrases that emphasize importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Directions
    -0.69
    Yeah
    -0.69
    umed
    -0.68
    leys
    -0.67
     Yeah
    -0.67
     Kills
    -0.64
    amber
    -0.64
     Daly
    -0.63
    lings
    -0.63
     Grants
    -0.62
    POSITIVE LOGITS
     overlooked
    0.78
     encaps
    0.77
     illuminating
    0.72
     seminal
    0.71
     underrated
    0.71
    ointed
    0.71
     distingu
    0.70
     fitting
    0.70
     noteworthy
    0.70
     notable
    0.69
    Activations Density 0.076%

    No Known Activations