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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 1148
    Prev
    Next
    INDEX
    Explanations

    references to the United States or activities involving the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.71
    MY
    -0.70
     refres
    -0.70
    inventoryQuantity
    -0.69
    plain
    -0.69
     [|
    -0.66
    ucci
    -0.64
     guiActiveUn
    -0.63
     srfAttach
    -0.61
    ttp
    -0.61
    POSITIVE LOGITS
     States
    1.46
     Nations
    1.33
     Kingdom
    1.17
     STATES
    1.08
     Methodist
    1.02
    States
    0.98
     Federation
    0.98
     Arab
    0.86
     Nation
    0.85
     State
    0.80
    Activations Density 0.031%

    No Known Activations