© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6261
    Prev
    Next
    INDEX
    Explanations

    words related to slowing or slowdown

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of slowing down or deceleration in various contexts

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

    No Comments

    Negative Logits
    esan
    -0.78
    ortium
    -0.76
    istle
    -0.74
    riad
    -0.73
    oral
    -0.71
    asel
    -0.68
    ince
    -0.67
    ersive
    -0.67
    atorial
    -0.66
     Responsibility
    -0.66
    POSITIVE LOGITS
     cooker
    1.08
     slowing
    0.91
     slows
    0.85
    downs
    0.85
     slowdown
    0.84
     down
    0.83
    DOWN
    0.83
     slower
    0.82
     speeding
    0.82
    down
    0.82
    Activations Density 0.017%

    No Known Activations