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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 7927
    Prev
    Next
    INDEX
    Explanations

    the phrase "the first time" followed by various contexts or events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant first-time events or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blah
    -0.72
     Favorite
    -0.72
     sucks
    -0.70
    terness
    -0.69
     wonderful
    -0.65
     meantime
    -0.64
     terrible
    -0.62
    Sad
    -0.62
     beaut
    -0.60
     hun
    -0.60
    POSITIVE LOGITS
    clusively
    1.01
     publicly
    1.01
     formally
    0.98
     openly
    0.97
     officially
    0.96
     EVER
    0.92
     explicitly
    0.92
    ever
    0.89
     remotely
    0.87
     fully
    0.84
    Activations Density 0.302%

    No Known Activations