© 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. 4-RES-JB
    11. 7444
    Prev
    Next
    INDEX
    Explanations

    phrases related to working hard or putting effort into tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to hard work or effort

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

    No Comments

    Negative Logits
     Tot
    -0.67
     Nest
    -0.66
    DATA
    -0.65
     Quarter
    -0.63
     Kut
    -0.63
     Sv
    -0.63
     Salvation
    -0.62
     Sut
    -0.61
     Expend
    -0.60
     Quin
    -0.60
    POSITIVE LOGITS
    esley
    0.80
    itud
    0.79
     enough
    0.79
    ened
    0.79
    balls
    0.77
     hard
    0.73
    entimes
    0.73
    ball
    0.72
    wired
    0.72
     harder
    0.71
    Activations Density 0.027%

    No Known Activations