© 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. 3-RES-JB
    11. 121
    Prev
    Next
    INDEX
    Explanations

    actions or instances of delay

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "delayed."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.87
    tained
    -0.86
    bern
    -0.84
    esan
    -0.79
    nai
    -0.79
    mbuds
    -0.78
    had
    -0.75
    ============
    -0.75
    ologue
    -0.73
     Institution
    -0.73
    POSITIVE LOGITS
     gratification
    1.08
     delaying
    1.05
     delayed
    1.04
     postp
    1.03
     puberty
    1.00
     delays
    0.99
     cancell
    0.91
     indefinitely
    0.87
     cooker
    0.87
     runaway
    0.85
    Activations Density 0.011%

    No Known Activations