© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9938
    Prev
    Next
    INDEX
    Explanations

    statements of enthusiasm or excitement

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or symbols often associated with excitement or anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     juggling
    -0.75
     scattering
    -0.72
     vom
    -0.69
    NetMessage
    -0.63
     tremend
    -0.63
     casting
    -0.63
     lodging
    -0.63
     dispers
    -0.61
     unmarked
    -0.60
     spiral
    -0.60
    POSITIVE LOGITS
    ¹
    0.84
    ¬
    0.83
    elong
    0.80
    ¢
    0.75
    ¯
    0.75
    agree
    0.74
    drivers
    0.73
    ISIS
    0.71
    aren
    0.70
    Xbox
    0.70
    Activations Density 0.431%

    No Known Activations