© 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. 3-RES-JB
    11. 6211
    Prev
    Next
    INDEX
    Explanations

    words related to determination and perseverance

    oai_token-act-pair · gpt-3.5-turbo

    the concept of determination or willpower

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.82
    WT
    -0.70
    ILA
    -0.69
    uese
    -0.69
    atha
    -0.68
    dayName
    -0.68
    athi
    -0.66
    awatts
    -0.66
    atern
    -0.65
    eah
    -0.65
    POSITIVE LOGITS
     compr
    0.73
     determined
    0.73
     determines
    0.71
     Lauder
    0.71
     determine
    0.69
    ly
    0.68
    ially
    0.66
     determination
    0.66
    lessly
    0.66
    LY
    0.63
    Activations Density 0.013%

    No Known Activations