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. 10106
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and organizations

    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
    862
    +0.10
    0.3%
    143
    +0.08
    0.2%
    1919
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    862
    +0.10
    0.06
    1919
    +0.08
    0.07
    143
    +0.08
    0.07
    Negative Logits
     obé
    -1.13
     répon
    -1.04
     écout
    -0.99
     représ
    -0.97
     soigne
    -0.96
     réuss
    -0.93
     recev
    -0.93
     pleins
    -0.93
     lola
    -0.92
     levis
    -0.92
    POSITIVE LOGITS
     participate
    0.68
     participated
    0.65
     agree
    0.65
     contributed
    0.63
     contribute
    0.58
     involved
    0.58
     joined
    0.57
     join
    0.55
     endorse
    0.55
     contacted
    0.55
    Activations Density 0.562%

    No Known Activations