© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 4234
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or recurring patterns in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with the word "Another."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liest
    -0.74
    alties
    -0.70
    isters
    -0.69
    ister
    -0.69
    âī
    -0.68
    hips
    -0.67
    email
    -0.66
    ola
    -0.65
    oper
    -0.64
    lee
    -0.64
    POSITIVE LOGITS
    worldly
    1.00
    vantage
    0.80
     drawback
    0.76
     unnamed
    0.73
     casualty
    0.72
    ngth
    0.72
    nces
    0.70
    alyst
    0.70
     undermin
    0.69
    ļéĨĴ
    0.68
    Activations Density 0.024%

    No Known Activations