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. 8432
    Prev
    Next
    INDEX
    Explanations

    phrases related to political commentary and societal issues

    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
    872
    +0.10
    0.3%
    674
    +0.08
    0.2%
    599
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.10
    0.04
    1159
    +0.08
    0.02
    734
    +0.07
    0.03
    Negative Logits
     Juf
    -1.08
     secon
    -1.06
     dises
    -1.05
     aen
    -1.04
     compen
    -1.03
     squa
    -1.00
     guarante
    -1.00
     aton
    -1.00
     mef
    -0.99
     stockholm
    -0.99
    POSITIVE LOGITS
     determines
    1.02
     depends
    0.93
     matters
    0.87
     determine
    0.83
     affects
    0.79
     decides
    0.78
     mattered
    0.75
     varies
    0.75
     matter
    0.74
     influences
    0.71
    Activations Density 0.370%

    No Known Activations