© 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. 1786
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the word "lot."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "a lot of."

    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
    ħĭ
    -0.92
    ĸļ
    -0.80
    ared
    -0.77
    acus
    -0.70
    aired
    -0.70
    usp
    -0.69
    ļéĨĴ
    -0.68
    nets
    -0.66
    =]
    -0.62
    NSA
    -0.62
    POSITIVE LOGITS
     interesting
    0.79
     surprises
    0.72
     fun
    0.71
     things
    0.70
     course
    0.68
     interest
    0.67
     sorts
    0.66
    icial
    0.65
     intermediate
    0.64
     luck
    0.64
    Activations Density 0.166%

    No Known Activations