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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6869
    Prev
    Next
    INDEX
    Explanations

    phrases related to the U.S. Federal Government and its agencies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Federal"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.81
    onge
    -0.77
    pered
    -0.74
     Clever
    -0.72
    paces
    -0.72
    ammers
    -0.72
    âĹ¼
    -0.71
    vier
    -0.70
    Downloadha
    -0.70
    enger
    -0.70
    POSITIVE LOGITS
     Reserve
    1.10
    ist
    0.87
    ists
    0.86
     Bureau
    0.83
     Election
    0.82
     Aviation
    0.79
     Credit
    0.79
     Institution
    0.78
     Government
    0.77
     Communications
    0.77
    Activations Density 0.013%

    No Known Activations