© 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. 10-RES-JB
    11. 24049
    Prev
    Next
    INDEX
    Explanations

    names related to Japanese culture

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names

    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
     Scotia
    -0.80
     neut
    -0.68
     Commonwealth
    -0.65
    ICE
    -0.61
     Capitals
    -0.61
    eering
    -0.60
     Unic
    -0.60
     RCMP
    -0.60
     Redux
    -0.60
     Rebels
    -0.59
    POSITIVE LOGITS
    amoto
    1.74
    azaki
    1.62
    amura
    1.45
    imura
    1.43
    ihara
    1.39
    asaki
    1.39
    imoto
    1.38
    ikawa
    1.32
    akura
    1.24
    aido
    1.21
    Activations Density 0.038%

    No Known Activations