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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 1240
    Prev
    Next
    INDEX
    Explanations

    references to Russian entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Russian."

    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
    Score
    -0.88
    ttes
    -0.76
    enance
    -0.75
    erer
    -0.75
    sbm
    -0.73
    Label
    -0.72
    Beck
    -0.72
    ayer
    -0.71
    oyer
    -0.71
    eter
    -0.70
    POSITIVE LOGITS
     Federation
    1.10
     olig
    0.95
     Orthodox
    0.95
    istani
    0.84
     rou
    0.83
     embassy
    0.82
     separatists
    0.82
     ambassador
    0.79
     Embassy
    0.79
     consulate
    0.77
    Activations Density 0.025%

    No Known Activations