© 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. 11-RES-JB
    11. 21286
    Prev
    Next
    INDEX
    Explanations

    time-related words like days, weeks, months, and years

    oai_token-act-pair · gpt-3.5-turbo

    quantities of time or duration-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    este
    -0.60
    versely
    -0.60
     Cosponsors
    -0.59
     ãĢĮ
    -0.58
    yrinth
    -0.56
    Cole
    -0.55
    agons
    -0.55
    ierrez
    -0.54
     Canter
    -0.53
    castle
    -0.53
    POSITIVE LOGITS
     worth
    1.18
    '
    0.93
     of
    0.89
     spent
    0.83
    hift
    0.81
     downtime
    0.76
     invested
    0.73
    '-
    0.73
    ynthesis
    0.73
    OF
    0.73
    Activations Density 0.148%

    No Known Activations