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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 8965
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "contract"

    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
    opping
    -0.73
     Flavoring
    -0.72
    apo
    -0.68
     Borough
    -0.68
     Sprite
    -0.67
    DonaldTrump
    -0.66
     cand
    -0.66
     Campus
    -0.65
    tical
    -0.65
    ablishment
    -0.64
    POSITIVE LOGITS
    ually
    1.09
     contract
    1.07
     contracts
    1.04
    ions
    0.97
    contract
    0.95
     negotiation
    0.87
     tender
    0.82
     contracted
    0.82
     renegoti
    0.81
     negotiations
    0.80
    Activations Density 0.021%

    No Known Activations