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. 4467
    Prev
    Next
    INDEX
    Explanations

    keywords related to storage and organization, particularly focusing on the action of "racking" items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "racking."

    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
     Austral
    -0.64
     Pesh
    -0.64
     Chomsky
    -0.64
     Human
    -0.63
     appropri
    -0.62
     Kot
    -0.62
     Kashmir
    -0.62
     Australian
    -0.61
     Oxy
    -0.61
     Chinese
    -0.61
    POSITIVE LOGITS
     rack
    1.26
     racks
    1.14
     Rack
    0.96
    mount
    0.94
    washer
    0.89
    ette
    0.84
    aign
    0.83
    ulic
    0.81
    artisan
    0.80
    yard
    0.79
    Activations Density 0.005%

    No Known Activations