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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24568
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Leave."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Leave" and "Remain" campaigns related to a specific event or discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.85
    £ı
    -0.68
     intest
    -0.68
     reconciliation
    -0.67
     exha
    -0.67
     flush
    -0.66
     HRC
    -0.64
    hips
    -0.64
     spitting
    -0.63
     offense
    -0.62
    POSITIVE LOGITS
     Leave
    1.41
     Remain
    1.03
    ndum
    1.01
     Yourself
    0.97
    Leave
    0.95
    oway
    0.92
    leave
    0.84
    wich
    0.84
    noon
    0.84
    cham
    0.82
    Activations Density 0.021%

    No Known Activations