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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-RES-JB
    6. 3248
    Prev
    Next
    INDEX
    Explanations

    references to the United Nations (UN)

    oai_token-act-pair · gpt-3.5-turbo

    the presence of references to the United Nations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Feldman
    -0.72
     conservatism
    -0.69
     constituency
    -0.65
     fascism
    -0.65
     shave
    -0.62
     goodbye
    -0.62
     Slate
    -0.62
     laz
    -0.62
     everything
    -0.61
     Sel
    -0.61
    POSITIVE LOGITS
    UN
    4.08
    UNE
    1.91
     UN
    1.78
    un
    1.65
    uns
    1.59
    UNCH
    1.39
    UL
    1.39
    unt
    1.38
    UM
    1.35
    OU
    1.34
    Activations Density 0.011%

    No Known Activations