© 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. 2-RES-JB
    11. 8285
    Prev
    Next
    INDEX
    Explanations

    words related to dust

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rylic
    -0.71
    going
    -0.71
    ulton
    -0.69
     Barbar
    -0.67
    amia
    -0.67
    oÄŁ
    -0.66
    istic
    -0.64
    ivia
    -0.63
    neg
    -0.63
    GBT
    -0.62
    POSITIVE LOGITS
     dust
    1.08
    bowl
    1.05
    Dust
    1.02
     grains
    0.87
    storms
    0.85
    bags
    0.84
    dust
    0.84
     clouds
    0.83
     Dust
    0.82
    bag
    0.82
    Activations Density 0.008%

    No Known Activations