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. 6-RES-JB
    6. 14293
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental dust events or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    references to dust and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istic
    -0.81
     Barbar
    -0.70
    ilitary
    -0.69
     autonomy
    -0.64
    rylic
    -0.63
    cers
    -0.62
    uilt
    -0.62
    GBT
    -0.62
    ntil
    -0.62
    upid
    -0.61
    POSITIVE LOGITS
    bowl
    1.22
     grains
    0.99
    Dust
    0.92
    storms
    0.91
    bag
    0.89
    iness
    0.89
    bags
    0.89
     dust
    0.88
    bin
    0.86
     jacket
    0.86
    Activations Density 0.016%

    No Known Activations