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. 428
    Prev
    Next
    INDEX
    Explanations

    names of a specific person, likely related to politics or public figures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Paul."

    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
     Mechdragon
    -0.67
     MacArthur
    -0.66
     2048
    -0.66
    åĤ
    -0.65
     Integrity
    -0.64
     Transparency
    -0.64
    CLE
    -0.63
    Environmental
    -0.63
    flush
    -0.63
    RFC
    -0.60
    POSITIVE LOGITS
    iflower
    1.65
    iffe
    1.07
    inations
    0.98
    oons
    0.94
    oaded
    0.93
    ibrary
    0.91
    atility
    0.87
    hemy
    0.85
    inator
    0.85
    itudes
    0.82
    Activations Density 0.013%

    No Known Activations