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

    Neuronpedia

    Jacobian LensNEW
    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. 11310
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and international affairs, specifically focusing on actions taken by political figures and potential consequences

    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
    2034
    +0.11
    0.3%
    856
    +0.10
    0.3%
    1183
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1081
    +0.11
    0.06
    1183
    +0.10
    0.04
    284
    +0.10
    0.05
    Negative Logits
     LIRE
    -0.83
     faudrait
    -0.82
     Enero
    -0.72
     febr
    -0.70
     FEBR
    -0.68
    Avez
    -0.68
    Rgds
    -0.67
     Lunes
    -0.66
     Água
    -0.65
    bonsoir
    -0.65
    POSITIVE LOGITS
     tramonto
    0.75
     göm
    0.72
     snapback
    0.67
     stork
    0.67
     vettore
    0.67
     outlander
    0.67
     schoolmaster
    0.65
     steamboat
    0.65
     bronco
    0.63
     drago
    0.63
    Activations Density 0.297%

    No Known Activations