© 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. 947
    Prev
    Next
    INDEX
    Explanations

    phrases related to delays

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delay."

    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
    ortium
    -0.93
    arov
    -0.91
    ramid
    -0.81
    rim
    -0.81
    tained
    -0.79
    bold
    -0.78
    kaya
    -0.74
    ophe
    -0.72
    rich
    -0.68
    ocene
    -0.68
    POSITIVE LOGITS
     gratification
    1.26
     delaying
    1.01
     delays
    0.89
     postp
    0.88
     cooker
    0.85
     indefinitely
    0.83
     delayed
    0.82
     Delay
    0.82
     delay
    0.81
     puberty
    0.78
    Activations Density 0.031%

    No Known Activations