© 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. 11-RES-JB
    11. 15689
    Prev
    Next
    INDEX
    Explanations

    words related to movement and speed

    oai_token-act-pair · gpt-3.5-turbo

    going rates of speed, particularly in the context of movement or travel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izo
    -0.80
    cro
    -0.72
    eria
    -0.66
    venant
    -0.65
     Pricing
    -0.63
    hole
    -0.62
    KNOWN
    -0.62
     Investigations
    -0.61
     Owners
    -0.61
    atto
    -0.61
    POSITIVE LOGITS
     speeds
    1.23
     superhuman
    1.01
     intervals
    1.00
     blinding
    0.98
     warp
    0.98
     lightning
    0.94
     unnatural
    0.94
     angles
    0.92
     alarming
    0.91
     leisure
    0.89
    Activations Density 0.095%

    No Known Activations