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. 6-RES-JB
    6. 17980
    Prev
    Next
    INDEX
    Explanations

    terms related to Brexit, such as "Brexit negotiator," "Brexit vote," and "Brexit impact papers."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Brexit and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONY
    -0.91
    oso
    -0.89
    OGR
    -0.86
    tops
    -0.83
    izen
    -0.77
    served
    -0.77
    seless
    -0.77
    iple
    -0.75
    SAM
    -0.74
    erve
    -0.74
    POSITIVE LOGITS
     referendum
    0.94
     Brexit
    0.87
     campaigner
    0.85
    Brexit
    0.80
     campaigners
    0.78
     repeal
    0.78
     Britain
    0.74
     negotiations
    0.72
     Countdown
    0.71
     Parliament
    0.71
    Activations Density 0.036%

    No Known Activations