© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24325
    Prev
    Next
    INDEX
    Explanations

    mentions of durations of time, particularly years

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the passage of time or duration of experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Alternatively
    -0.89
    Elsewhere
    -0.79
     alternatives
    -0.67
     substitutes
    -0.66
     explanatory
    -0.63
     thumbnail
    -0.63
     Alternatively
    -0.61
     moderates
    -0.61
     lieu
    -0.61
    isk
    -0.60
    POSITIVE LOGITS
    inguished
    0.89
     spanning
    0.85
     countless
    0.79
    interrupted
    0.77
    htaking
    0.77
     culminating
    0.77
    nob
    0.76
     witnessing
    0.72
    ldom
    0.72
    living
    0.71
    Activations Density 0.492%

    No Known Activations