© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 16107
    Prev
    Next
    INDEX
    Explanations

    mentions of something increasing rapidly

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "ramping up" or increasing intensity or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pedia
    -0.71
    ternity
    -0.71
    creen
    -0.69
     Confederation
    -0.65
     Comet
    -0.64
    nery
    -0.63
     Cause
    -0.62
    KNOWN
    -0.62
    ãĥĨãĤ£
    -0.61
    DOM
    -0.61
    POSITIVE LOGITS
    aging
    1.17
    arts
    1.02
    up
    0.98
    ages
    0.96
    hetamine
    0.92
    aged
    0.91
    antly
    0.90
    ups
    0.87
    inson
    0.84
    age
    0.82
    Activations Density 0.033%

    No Known Activations