Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 10135
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or economic sanctions

    oai_token-act-pair · gpt-3.5-turbo

    references to sanctions and their enforcement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -1.11
    uscript
    -0.78
    ITNESS
    -0.75
    erd
    -0.74
     Lives
    -0.70
    itness
    -0.70
    pheus
    -0.69
     Prest
    -0.69
    WORK
    -0.68
     Alic
    -0.68
    POSITIVE LOGITS
     imposed
    1.24
     levied
    1.22
     relief
    1.21
     sanctions
    1.12
     regimes
    1.10
     regime
    1.06
     embargo
    1.03
     prohibiting
    0.95
     targeting
    0.94
     sanction
    0.89
    Activations Density 0.056%

    No Known Activations