© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23625
    Prev
    Next
    INDEX
    Explanations

    contract-related terms, particularly contract terminations and new contract signings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "contract" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.72
    joy
    -0.71
    opping
    -0.68
    cn
    -0.67
     Flavoring
    -0.66
    ankind
    -0.65
    olute
    -0.65
    ablishment
    -0.64
    hua
    -0.64
     Alto
    -0.64
    POSITIVE LOGITS
    ually
    1.08
     contracts
    0.99
     contract
    0.95
    ions
    0.91
     negotiation
    0.91
     renegoti
    0.90
     negotiations
    0.84
    contract
    0.81
    heed
    0.80
    rays
    0.80
    Activations Density 0.021%

    No Known Activations