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. 3-RES-JB
    6. 2277
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bilateral" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to bilateral agreements or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oxide
    -0.84
    RAM
    -0.82
    enment
    -0.81
    nit
    -0.80
    tro
    -0.80
    RANT
    -0.79
    ride
    -0.79
    roller
    -0.77
    arde
    -0.76
    rors
    -0.76
    POSITIVE LOGITS
     bilateral
    1.11
     relations
    0.97
     engagements
    0.93
     handshake
    0.91
     dealings
    0.88
    ilateral
    0.88
     symmetry
    0.85
     cooperation
    0.84
     transact
    0.84
     undert
    0.83
    Activations Density 0.009%

    No Known Activations