© 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. 9920
    Prev
    Next
    INDEX
    Explanations

    the phrase "to this day."

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the idea of continuity or persistence over time

    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
    thumbnails
    -0.81
    packages
    -0.75
    ickets
    -0.73
    apes
    -0.71
    Vers
    -0.68
    agi
    -0.68
    ãĤ¹ãĥĪ
    -0.67
    姫
    -0.66
    cases
    -0.65
    resses
    -0.65
    POSITIVE LOGITS
     point
    1.17
     day
    0.99
     jun
    0.93
     moment
    0.92
     date
    0.92
     standpoint
    0.86
     fateful
    0.83
     end
    0.82
     reasoning
    0.80
     stage
    0.77
    Activations Density 0.056%

    No Known Activations