© 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. 11770
    Prev
    Next
    INDEX
    Explanations

    sentences related to shifts or changes, particularly in the context of media or information dissemination

    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
    198
    +0.10
    0.3%
    678
    +0.10
    0.3%
    752
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.10
    0.05
    678
    +0.10
    0.05
    752
    +0.08
    0.04
    Negative Logits
     ejus
    -0.63
     fince
    -0.59
     shewn
    -0.58
     excru
    -0.56
     pite
    -0.55
     snoopy
    -0.55
     quæ
    -0.55
     conforman
    -0.54
     ujednoznacz
    -0.53
     Marín
    -0.53
    POSITIVE LOGITS
     digital
    0.86
     online
    0.84
     electronic
    0.79
     electronically
    0.76
    digital
    0.76
     digitale
    0.74
    online
    0.73
     digitally
    0.72
     Online
    0.71
     computer
    0.71
    Activations Density 0.626%

    No Known Activations