© 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. 2-RES-JB
    11. 15809
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Henri"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Henri

    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
     rating
    -0.72
     bargain
    -0.72
    raviolet
    -0.70
    AFTA
    -0.69
     bund
    -0.68
    ungle
    -0.68
     filings
    -0.68
    ulhu
    -0.67
    anke
    -0.67
     raiding
    -0.67
    POSITIVE LOGITS
    etta
    0.98
    ques
    0.95
     Henri
    0.89
    liness
    0.89
     Lauder
    0.85
    ����
    0.84
     Emer
    0.82
    ============
    0.82
    quez
    0.80
    clus
    0.80
    Activations Density 0.022%

    No Known Activations