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. 18281
    Prev
    Next
    INDEX
    Explanations

    mentions of international relations and political cooperation

    oai_token-act-pair · gpt-3.5-turbo

    references to political entities and relationships

    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
     Heist
    -0.71
    NetMessage
    -0.70
     Purg
    -0.66
     partName
    -0.65
    ymm
    -0.63
    ]}
    -0.63
    ãĥĩãĤ£
    -0.61
    SHIP
    -0.60
    ]=
    -0.60
    undle
    -0.59
    POSITIVE LOGITS
     buddies
    0.68
     Kardash
    0.68
    omever
    0.67
    neau
    0.66
     partners
    0.65
     colleagues
    0.64
     representatives
    0.62
     contractor
    0.61
    eteria
    0.61
     mates
    0.60
    Activations Density 0.595%

    No Known Activations