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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 18336
    Prev
    Next
    INDEX
    Explanations

    phrases related to dialogue, including interruptions and statements within a conversation

    oai_token-act-pair · gpt-3.5-turbo

    instances of interruptions or pauses in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ°
    -0.75
    SourceFile
    -0.73
    osate
    -0.73
    Reloaded
    -0.68
     Citiz
    -0.68
    é¾
    -0.68
     Droid
    -0.66
    ozyg
    -0.65
    ा
    -0.64
    à¥
    -0.64
    POSITIVE LOGITS
     uh
    1.08
    yeah
    0.96
     yeah
    0.94
     um
    0.92
    you
    0.87
    Yeah
    0.81
     gasp
    0.79
    shall
    0.78
    what
    0.77
    fuck
    0.77
    Activations Density 0.135%

    No Known Activations