© 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. 22025
    Prev
    Next
    INDEX
    Explanations

    ellipsis (...) used to indicate a trailing off of thought or a pause in speech

    oai_token-act-pair · gpt-3.5-turbo

    ellipses indicating pauses or omissions in dialogue or narrative

    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
    icum
    -0.85
    oit
    -0.83
    oresc
    -0.78
    enei
    -0.71
    ulence
    -0.71
    osate
    -0.71
    odi
    -0.70
    ¶ħ
    -0.70
    åŃIJ
    -0.68
    berra
    -0.68
    POSITIVE LOGITS
    BUT
    0.94
     Written
    0.83
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    0.72
     Wait
    0.70
     Continue
    0.70
    âĢ¦âĢ¦âĢ¦âĢ¦
    0.69
     Appears
    0.68
    wait
    0.68
     Goo
    0.64
    .....
    0.64
    Activations Density 0.013%

    No Known Activations