© 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. 11-RES-JB
    11. 10104
    Prev
    Next
    INDEX
    Explanations

    terms related to diplomatic activities and operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to diplomatic activities and personnel

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nings
    -0.70
     Progressive
    -0.66
     Hemp
    -0.63
     payday
    -0.62
    Plex
    -0.59
    efer
    -0.59
    payer
    -0.59
     Panther
    -0.59
     Disorder
    -0.58
    omsday
    -0.58
    POSITIVE LOGITS
    assies
    1.15
     diplomats
    0.99
    assador
    0.96
     Kislyak
    0.95
    assadors
    0.94
     cables
    0.89
     diplomat
    0.89
     abroad
    0.89
     embassies
    0.89
     embassy
    0.87
    Activations Density 0.097%

    No Known Activations