© 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. 10-RES-JB
    11. 13770
    Prev
    Next
    INDEX
    Explanations

    phrases related to repetition or continuity over time

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "time and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.83
    Surv
    -0.76
    igers
    -0.73
    fect
    -0.72
    iors
    -0.71
    irens
    -0.67
     Receiver
    -0.66
    quart
    -0.66
     Prot
    -0.65
    ģĸ
    -0.65
    POSITIVE LOGITS
     space
    1.07
     resources
    0.95
     patience
    0.94
     energy
    0.93
     effort
    0.93
     manpower
    0.90
     money
    0.89
     place
    0.89
     expense
    0.86
     inclination
    0.84
    Activations Density 0.065%

    No Known Activations