© 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. 2813
    Prev
    Next
    INDEX
    Explanations

    phrases involving personal knowledge or premonition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I knew" indicating awareness or prior knowledge

    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
    phrine
    -0.80
    atre
    -0.79
    ãĤ´ãĥ³
    -0.78
    pmwiki
    -0.78
    uries
    -0.73
    ciation
    -0.71
    ItemTracker
    -0.69
    orio
    -0.65
    onding
    -0.65
    adies
    -0.65
    POSITIVE LOGITS
     beforehand
    1.23
     instinctively
    0.98
     exactly
    0.88
     nothing
    0.88
    nothing
    0.82
     something
    0.81
     better
    0.80
     intimately
    0.80
     firsthand
    0.79
     darn
    0.78
    Activations Density 0.067%

    No Known Activations