© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7477
    Prev
    Next
    INDEX
    Explanations

    mentions of international sanctions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.14
    0.5%
    1691
    +0.13
    0.5%
    1472
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.14
    0.02
    1472
    +0.13
    0.02
    411
    +0.13
    0.02
    Negative Logits
     inder
    -0.82
     pessi
    -0.82
     curi
    -0.82
     bose
    -0.82
     reger
    -0.81
     blin
    -0.81
     nutella
    -0.79
     intermitt
    -0.77
     fluo
    -0.76
     vogli
    -0.76
    POSITIVE LOGITS
     sanctions
    1.21
     Sanctions
    0.98
     sanction
    0.92
     sanctioned
    0.79
    San
    0.75
     San
    0.70
    san
    0.68
     san
    0.66
     SAN
    0.62
    SAN
    0.59
    Activations Density 0.080%

    No Known Activations