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. 707
    Prev
    Next
    INDEX
    Explanations

    information related to political controversy and government surveillance practices

    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
    198
    +0.16
    0.5%
    50
    +0.09
    0.2%
    1938
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.16
    0.06
    1600
    +0.09
    0.05
    1938
    +0.08
    0.05
    Negative Logits
    <bos>
    -0.54
    ambiguation
    -0.48
     glabrous
    -0.47
     policiais
    -0.46
     foramen
    -0.46
    ErrorException
    -0.42
     voordat
    -0.42
    éhez
    -0.42
    AndFlush
    -0.41
     bacilli
    -0.41
    POSITIVE LOGITS
     exé
    1.03
     soigne
    0.91
     Gorb
    0.87
     BIBSYS
    0.86
     déplo
    0.85
     Khart
    0.85
     Souha
    0.84
     Augu
    0.83
     démission
    0.81
     Juf
    0.81
    Activations Density 0.389%

    No Known Activations