© 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. 9975
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly focusing on the name "Manuel"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Manuel or Emmanuel

    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
    ãĤ´ãĥ³
    -0.78
    hedral
    -0.77
    ertility
    -0.75
    ewater
    -0.74
    othal
    -0.71
    lease
    -0.67
    dfx
    -0.66
    burgh
    -0.66
    agra
    -0.66
    earch
    -0.64
    POSITIVE LOGITS
    ique
    0.96
     Macron
    0.91
    angelo
    0.90
    ians
    0.85
     Miranda
    0.82
     Santos
    0.81
     Castro
    0.80
    itte
    0.80
    icans
    0.78
    itous
    0.77
    Activations Density 0.045%

    No Known Activations