© 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. 8-RES-JB
    11. 18508
    Prev
    Next
    INDEX
    Explanations

    mentions of overtime situations or references in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to overtime in sports or work contexts

    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
    ystem
    -0.80
    kie
    -0.76
    sonian
    -0.75
    friend
    -0.71
    info
    -0.71
    ,,,,,,,,
    -0.70
    =-=-=-=-=-=-=-=-
    -0.70
     Aj
    -0.70
    ydia
    -0.69
    leon
    -0.69
    POSITIVE LOGITS
     stopp
    0.75
     msec
    0.74
     penalty
    0.71
     overtime
    0.64
    icum
    0.64
     Wonderland
    0.64
    rites
    0.64
     periods
    0.63
     hours
    0.63
     accrued
    0.61
    Activations Density 0.066%

    No Known Activations