© 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. 2-RES-JB
    11. 9195
    Prev
    Next
    INDEX
    Explanations

    phrases related to different medical occupations or fields of study

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly related to roles or titles

    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
    jriwal
    -0.57
     largeDownload
    -0.56
     Shutterstock
    -0.55
    ĸļ
    -0.54
    */(
    -0.52
    rawdownloadcloneembedreportprint
    -0.52
     blasp
    -0.51
    displayText
    -0.50
     craw
    -0.49
    HCR
    -0.48
    POSITIVE LOGITS
    ette
    0.69
    age
    0.66
    ée
    0.66
    opt
    0.63
    ete
    0.62
    etric
    0.62
    ix
    0.59
    ale
    0.59
    estone
    0.59
    ote
    0.59
    Activations Density 0.837%

    No Known Activations