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. 4-RES-JB
    6. 5433
    Prev
    Next
    INDEX
    Explanations

    phrases related to contractual agreements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "agreement."

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

    No Comments

    Negative Logits
    culus
    -0.75
    gun
    -0.73
    bish
    -0.73
    asus
    -0.71
    milo
    -0.70
    bull
    -0.69
    etsk
    -0.68
    castle
    -0.67
    population
    -0.67
    gm
    -0.65
    POSITIVE LOGITS
     agreement
    1.19
    reements
    1.13
     Agreement
    1.11
     agreements
    1.09
     treaty
    1.01
    reement
    0.97
     negotiated
    0.96
     treaties
    0.95
    ually
    0.93
     negotiation
    0.92
    Activations Density 0.027%

    No Known Activations