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. 6022
    Prev
    Next
    INDEX
    Explanations

    mentions or abbreviations related to the European Parliament (EP)

    oai_token-act-pair · gpt-3.5-turbo

    the acronym "EP" and its variations, likely related to a specific entity or organization

    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
     caster
    -0.77
     Sands
    -0.68
     otherwise
    -0.68
     Dracula
    -0.66
     Rite
    -0.65
     thirds
    -0.65
     Fant
    -0.63
     Curse
    -0.63
     Heroes
    -0.62
     Saudi
    -0.62
    POSITIVE LOGITS
    EP
    1.23
    odcast
    1.15
    oleon
    1.08
    HER
    0.97
    rint
    0.97
    ilon
    0.96
    olicy
    0.88
    hemer
    0.88
    awei
    0.87
    iphany
    0.85
    Activations Density 0.005%

    No Known Activations