© 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 EvalsExportsinterp-engineNEWAPI 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. 4921
    Prev
    Next
    INDEX
    Explanations

    terms related to global political conflicts and events

    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
    1741
    +0.18
    0.6%
    227
    +0.10
    0.3%
    1177
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.18
    0.06
    227
    +0.10
    0.07
    1852
    +0.09
    0.06
    Negative Logits
    .
    -0.56
     createContext
    -0.55
    VELOP
    -0.54
     withRouter
    -0.53
    ↵↵
    -0.52
     soeur
    -0.51
    <bos>
    -0.51
     soweit
    -0.51
     OrderedDict
    -0.50
    ALLENG
    -0.49
    POSITIVE LOGITS
     Præ
    1.21
     aen
    1.17
     Juf
    1.14
     oun
    1.10
     fta
    1.10
     gend
    1.10
     mef
    1.10
     Godt
    1.08
     tew
    1.07
     ivi
    1.06
    Activations Density 0.426%

    No Known Activations