© 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. 7-RES-JB
    11. 12372
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "now" with some negative connotation following it

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "now" and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EntityItem
    -0.81
     Rodgers
    -0.77
     Tolkien
    -0.77
     Cohn
    -0.76
     Polo
    -0.74
     Rica
    -0.73
     Orchestra
    -0.73
     ROCK
    -0.72
     Howe
    -0.71
     Dickinson
    -0.71
    POSITIVE LOGITS
    existing
    1.20
    famous
    1.18
    develop
    1.12
    defined
    1.04
    dead
    1.03
    announced
    1.03
    mentioned
    1.03
    rising
    1.01
    inc
    0.99
    numbered
    0.98
    Activations Density 0.060%

    No Known Activations