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. 3-RES-JB
    6. 14623
    Prev
    Next
    INDEX
    Explanations

    names related to Russian individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their connections to Russia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NCT
    -0.77
    }}}
    -0.75
    uckland
    -0.75
    prototype
    -0.74
     Wick
    -0.74
    dash
    -0.72
     Wad
    -0.71
    jc
    -0.70
    alist
    -0.70
     Nou
    -0.66
    POSITIVE LOGITS
     dossier
    1.08
     subpoen
    0.96
     intelligence
    0.93
     subpoena
    0.92
    ghazi
    0.91
     spying
    0.89
     Kislyak
    0.88
    FBI
    0.88
     inappropriately
    0.87
     blackmail
    0.87
    Activations Density 0.052%

    No Known Activations