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. 14385
    Prev
    Next
    INDEX
    Explanations

    terms related to the political event of Brexit

    oai_token-act-pair · gpt-3.5-turbo

    references to Brexit

    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
    ONY
    -0.88
    oso
    -0.85
    tops
    -0.82
    OGR
    -0.82
    served
    -0.79
    seless
    -0.78
    SAM
    -0.73
    selage
    -0.71
    iple
    -0.71
    asus
    -0.70
    POSITIVE LOGITS
     referendum
    0.93
     Brexit
    0.92
     campaigner
    0.87
    Brexit
    0.84
     campaigners
    0.78
     2020
    0.77
     negotiations
    0.72
     repeal
    0.72
     Countdown
    0.72
     Cabinet
    0.71
    Activations Density 0.027%

    No Known Activations