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. 15771
    Prev
    Next
    INDEX
    Explanations

    information related to government officials, political affiliations, and administrative roles

    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
    1499
    +0.11
    0.3%
    1403
    +0.10
    0.3%
    806
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.11
    0.11
    939
    +0.10
    0.08
    806
    +0.09
    0.05
    Negative Logits
    Hahahahaha
    -1.05
    Hahah
    -1.01
    Lmfao
    -1.00
     pikachu
    -0.99
     spiderman
    -0.98
     yoda
    -0.97
     hentai
    -0.96
    Ehh
    -0.95
     hairc
    -0.95
    Ohhhh
    -0.94
    POSITIVE LOGITS
     teras
    1.05
     Öster
    0.96
     Spani
    0.93
     Amerik
    0.93
     silikon
    0.92
     saar
    0.92
     kule
    0.90
     Jä
    0.90
     alkoh
    0.87
     traktor
    0.86
    Activations Density 1.258%

    No Known Activations