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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 18283
    Prev
    Next
    INDEX
    Explanations

    phrases related to politics, specifically mentions of the White House

    oai_token-act-pair · gpt-3.5-turbo

    references to the White House

    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
     exting
    -1.02
     eleph
    -0.95
     pione
    -0.94
     practition
    -0.91
    Þ
    -0.88
    aditional
    -0.88
     tremend
    -0.87
     occas
    -0.87
    ò
    -0.87
    ortunately
    -0.84
    POSITIVE LOGITS
    lace
    0.47
    forge
    0.47
     Angeles
    0.47
    asury
    0.47
    ashington
    0.46
    leground
    0.46
    ennis
    0.46
     Seed
    0.45
     States
    0.45
     Cabinet
    0.44
    Activations Density 0.131%

    No Known Activations