© 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. 13863
    Prev
    Next
    INDEX
    Explanations

    quotations in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "said."

    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
    pee
    -0.87
    ãĤ¼ãĤ¦ãĤ¹
    -0.85
    Enlarge
    -0.82
    bernatorial
    -0.78
    pees
    -0.77
    zona
    -0.75
    ILA
    -0.74
    NPR
    -0.74
    colored
    -0.73
    lator
    -0.72
    POSITIVE LOGITS
     organisers
    1.07
     afterwards
    0.99
     whilst
    0.99
     £
    0.97
     apologised
    0.96
     Britons
    0.93
     enqu
    0.91
    :"
    0.90
     criticised
    0.90
     although
    0.87
    Activations Density 0.142%

    No Known Activations