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. 1-RES-JB
    6. 18364
    Prev
    Next
    INDEX
    Explanations

    words related to vacuum or empty space

    oai_token-act-pair · gpt-3.5-turbo

    references to vacuum-related concepts and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cs
    -0.75
    gd
    -0.72
    igel
    -0.70
    kt
    -0.70
    ews
    -0.69
    dule
    -0.67
    ione
    -0.66
    eworld
    -0.66
    thus
    -0.66
    hig
    -0.65
    POSITIVE LOGITS
     vacuum
    1.21
     cleaners
    1.05
     cleaner
    1.02
    ategory
    0.86
     ventilation
    0.80
    ãĤ©
    0.76
     oven
    0.76
    Þ
    0.73
     aspiration
    0.73
     centrif
    0.70
    Activations Density 0.008%

    No Known Activations