© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 17161
    Prev
    Next
    INDEX
    Explanations

    names related to the Han dynasty

    oai_token-act-pair · gpt-3.5-turbo

    the name "Han" mentioned in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tsky
    -0.67
    ODUCT
    -0.60
     impunity
    -0.59
     Oath
    -0.58
    Reloaded
    -0.58
     describ
    -0.56
     pneum
    -0.56
     Integ
    -0.54
     Colossus
    -0.53
     tubes
    -0.53
    POSITIVE LOGITS
    auer
    1.21
    lon
    1.16
    over
    1.07
     Solo
    1.07
    uman
    1.06
    ako
    1.05
    nington
    1.03
    wei
    1.00
    amura
    0.99
    retty
    0.98
    Activations Density 0.029%

    No Known Activations