© 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. 642
    Prev
    Next
    INDEX
    Explanations

    the name "Juan" with a strong emphasis on the variant spelling "Juan"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Duan" and its variations as well as mentions of other individuals associated with that name

    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
     Elys
    -0.69
     CoC
    -0.64
     Revelations
    -0.64
     Pixie
    -0.63
     javascript
    -0.61
    ãģĨ
    -0.61
    Ö¼
    -0.60
     Ajax
    -0.59
     Skydragon
    -0.59
    é¾įå¥ij士
    -0.58
    POSITIVE LOGITS
    igans
    1.05
    assis
    0.99
    uan
    0.93
    wu
    0.92
    iverse
    0.91
    idad
    0.88
    ua
    0.88
    zac
    0.85
    ghai
    0.84
    cient
    0.84
    Activations Density 0.009%

    No Known Activations