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. 3059
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreements, contracts, or deals

    oai_token-act-pair · gpt-3.5-turbo

    references to agreements or treaties

    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
    visors
    -0.74
    cyl
    -0.68
    asury
    -0.68
    \\\\\\\\\\\\\\\\
    -0.65
    eared
    -0.63
    gallery
    -0.62
     Holding
    -0.61
    utch
    -0.60
     Armored
    -0.59
    DonaldTrump
    -0.59
    POSITIVE LOGITS
     pact
    1.31
     Pact
    0.89
     reneg
    0.83
     renegoti
    0.81
    isphere
    0.78
    reement
    0.77
    hered
    0.76
    ãĥ¼ãĥĨ
    0.76
    ãĥ¼ãĥĨãĤ£
    0.75
     handshake
    0.75
    Activations Density 0.006%

    No Known Activations