© 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. 2497
    Prev
    Next
    INDEX
    Explanations

    words related to Chinese names

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities associated with specific actions or events

    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
     Odyssey
    -0.83
     TBD
    -0.73
    brance
    -0.73
     ALE
    -0.73
     Valhalla
    -0.71
     ATT
    -0.70
     Bosnia
    -0.70
     Parad
    -0.69
     Redux
    -0.69
     Satanic
    -0.69
    POSITIVE LOGITS
    uan
    1.56
    iang
    1.52
    ao
    1.48
    iao
    1.47
    uo
    1.45
    ijing
    1.42
    ui
    1.42
    hao
    1.40
    ong
    1.40
    iu
    1.39
    Activations Density 0.087%

    No Known Activations