© 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. 2-RES-JB
    11. 19029
    Prev
    Next
    INDEX
    Explanations

    phrases related to delays

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delayed" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bern
    -0.98
    tained
    -0.90
    tain
    -0.81
    nai
    -0.81
    mbuds
    -0.77
    ortium
    -0.76
     Institution
    -0.76
    had
    -0.76
    esan
    -0.75
    onym
    -0.74
    POSITIVE LOGITS
     delayed
    1.14
     postp
    1.03
     gratification
    1.03
     cancell
    0.99
     delays
    0.98
     delaying
    0.94
     puberty
    0.93
     adolesc
    0.93
     runaway
    0.90
     satell
    0.86
    Activations Density 0.014%

    No Known Activations