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. 3443
    Prev
    Next
    INDEX
    Explanations

    words related to sudden increases or surges

    oai_token-act-pair · gpt-3.5-turbo

    references to sudden increases or spikes in various metrics or phenomena

    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
    iar
    -0.81
     Narr
    -0.76
     Jiu
    -0.71
     Lod
    -0.71
     entrusted
    -0.68
     envis
    -0.68
    Ãī
    -0.67
    ropri
    -0.67
    atis
    -0.66
     Franç
    -0.66
    POSITIVE LOGITS
     spike
    3.62
     spikes
    3.20
     spiked
    2.43
     uptick
    1.74
     surge
    1.66
     Spike
    1.59
     surges
    1.42
     skyrocket
    1.28
     peak
    1.25
     peaks
    1.20
    Activations Density 0.018%

    No Known Activations