© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3429
    Prev
    Next
    INDEX
    Explanations

    phrases related to confusion or lack of understanding

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the concept of "going on," indicating a search for clarity or understanding in a situation

    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
    gart
    -0.72
    vale
    -0.65
    ament
    -0.59
    inates
    -0.57
    stra
    -0.54
    adjusted
    -0.54
    aments
    -0.52
     Desk
    -0.52
     rede
    -0.52
     relinqu
    -0.51
    POSITIVE LOGITS
     wrong
    0.91
     happening
    0.80
     viral
    0.75
     Wrong
    0.71
     happen
    0.70
    wrong
    0.70
    ãĥ£
    0.69
    ggle
    0.69
    lems
    0.69
    æĸ¹
    0.68
    Activations Density 0.031%

    No Known Activations