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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 48
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a large quantity or amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing abundance or quantity

    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
    emaker
    -0.66
     directive
    -0.66
    acea
    -0.65
    tip
    -0.62
    blance
    -0.62
    cone
    -0.61
    star
    -0.61
    bert
    -0.59
    speak
    -0.59
    cture
    -0.59
    POSITIVE LOGITS
     lots
    3.36
     Lots
    2.41
    Lots
    2.02
     plenty
    1.92
     tons
    1.90
     LOT
    1.84
     lot
    1.72
     loads
    1.70
     alot
    1.58
     tonnes
    1.23
    Activations Density 0.013%

    No Known Activations