© 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. 11-RES-JB
    11. 20427
    Prev
    Next
    INDEX
    Explanations

    words related to attempts or efforts

    oai_token-act-pair · gpt-3.5-turbo
    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
    ahu
    -0.58
    amaz
    -0.55
    inth
    -0.55
    cised
    -0.54
    hea
    -0.54
    requisite
    -0.53
    scar
    -0.52
    icka
    -0.51
    marks
    -0.51
    dylib
    -0.50
    POSITIVE LOGITS
     desperately
    1.10
     unsuccessfully
    1.02
     to
    0.96
     harder
    0.93
     hard
    0.87
     valiant
    0.87
     vain
    0.78
     frantically
    0.76
     toget
    0.74
    hard
    0.73
    Activations Density 0.054%

    No Known Activations