© 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. 10-RES-JB
    11. 13996
    Prev
    Next
    INDEX
    Explanations

    names with a variation of the sequence of letters "han"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Han" and its various forms or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ongyang
    -0.80
     plur
    -0.58
     Seym
    -0.58
    course
    -0.58
    yers
    -0.58
    suit
    -0.57
    lled
    -0.57
    REE
    -0.56
     course
    -0.56
     detrim
    -0.55
    POSITIVE LOGITS
    igans
    1.43
    ovich
    1.19
    ews
    1.18
    igan
    1.17
    ovic
    1.16
    ova
    1.15
    ese
    1.15
    thal
    1.11
    omics
    1.11
    ufact
    1.07
    Activations Density 0.107%

    No Known Activations