© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 6480
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Nan" which is likely a proper noun or a technical term in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Nano" and related technology

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    âķIJâķIJ
    -0.77
    ————————————————
    -0.73
    ORY
    -0.69
    DIT
    -0.66
     Jarrett
    -0.66
    ãĤ¦
    -0.65
    Magikarp
    -0.65
    lift
    -0.65
     Scand
    -0.64
    EEP
    -0.63
    POSITIVE LOGITS
     Nan
    1.26
    ocry
    1.09
    omach
    1.05
    otechnology
    1.00
    igans
    0.97
    otech
    0.93
     hous
    0.91
    ufact
    0.91
    jing
    0.89
    awan
    0.89
    Activations Density 0.004%

    No Known Activations