© 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. 15682
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant time periods or anniversaries

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of many years

    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
    ople
    -0.84
    icum
    -0.76
    iqu
    -0.75
    eus
    -0.72
    etsk
    -0.69
    apa
    -0.68
    achus
    -0.68
    anus
    -0.66
     subp
    -0.65
    anooga
    -0.65
    POSITIVE LOGITS
     ago
    1.37
     olds
    1.07
     Ago
    1.05
     old
    0.94
     hindsight
    0.89
     nostalg
    0.84
     anniversary
    0.78
     overdue
    0.77
     apiece
    0.76
     Anniversary
    0.73
    Activations Density 0.095%

    No Known Activations