© 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. 3-RES-JB
    11. 5145
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Per"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Per."

    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
    å¸
    -0.86
    SpaceEngineers
    -0.77
    enegger
    -0.76
    INESS
    -0.74
    ãģı
    -0.72
    ãģ®å®
    -0.69
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    ģĸ
    -0.67
    ç·
    -0.67
    ä
    -0.66
    POSITIVE LOGITS
     capita
    1.08
    due
    1.06
    secut
    1.05
    forming
    1.04
    secution
    1.02
    iod
    1.01
    ceptions
    1.00
    ipher
    0.96
    missible
    0.96
    formed
    0.95
    Activations Density 0.012%

    No Known Activations