© 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. 7-RES-JB
    11. 18076
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a passage of time, especially focusing on "after years of" phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference a duration or period of time

    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
    anooga
    -0.83
     Cosponsors
    -0.72
    ÙIJ
    -0.72
    article
    -0.72
    epad
    -0.71
    deck
    -0.70
    paces
    -0.70
    ombies
    -0.70
    rider
    -0.70
    acus
    -0.70
    POSITIVE LOGITS
     uninterrupted
    1.01
     campaigning
    0.92
     struggle
    0.92
     accumulated
    0.92
     reckoning
    0.87
     frustration
    0.85
     unsuccessful
    0.83
     silence
    0.82
     accumulating
    0.82
     probation
    0.81
    Activations Density 0.063%

    No Known Activations