Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14242
    Prev
    Next
    INDEX
    Explanations

    mention of the name "Bush"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bush administration

    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
    semble
    -0.70
    helle
    -0.69
    ances
    -0.69
     Qiao
    -0.64
     Adin
    -0.63
    photos
    -0.62
    hooting
    -0.61
     Cth
    -0.60
     Yao
    -0.60
     Frem
    -0.60
    POSITIVE LOGITS
    nell
    1.23
    ido
    1.13
    master
    1.02
     Sr
    0.97
    wick
    0.92
     Bush
    0.91
     Hussein
    0.90
    Bush
    0.87
    men
    0.86
     Administration
    0.83
    Activations Density 0.030%

    No Known Activations