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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8255
    Prev
    Next
    INDEX
    Explanations

    situations or elements related to geopolitical 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
    645
    +0.10
    0.3%
    1044
    +0.08
    0.2%
    1438
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.10
    0.04
    172
    +0.08
    0.03
    789
    +0.08
    0.02
    Negative Logits
     reluct
    -1.83
     disagre
    -1.78
     increa
    -1.76
     shenan
    -1.73
     encomp
    -1.69
     impra
    -1.68
     depic
    -1.68
     indestru
    -1.67
     unspeak
    -1.64
     inconce
    -1.63
    POSITIVE LOGITS
     useCallback
    0.69
    also
    0.64
     also
    0.64
     weil
    0.64
     também
    0.62
     importantly
    0.62
     también
    0.61
     ook
    0.60
     också
    0.60
     ALSO
    0.60
    Activations Density 0.183%

    No Known Activations