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. 10034
    Prev
    Next
    INDEX
    Explanations

    contemporary political and social 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
    381
    +0.14
    0.4%
    468
    +0.14
    0.4%
    658
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    599
    +0.14
    0.08
    1919
    +0.14
    0.07
    1415
    +0.10
    0.04
    Negative Logits
     ecru
    -1.58
     suscep
    -1.57
     impra
    -1.56
     squa
    -1.53
     swarovski
    -1.53
     embodi
    -1.52
     secon
    -1.52
     lamborghini
    -1.49
     murano
    -1.48
     excru
    -1.48
    POSITIVE LOGITS
    ,"
    0.99
    ,”
    0.98
    ",
    0.88
    ”,
    0.87
    "),
    0.84
    ”
    0.82
    ,'
    0.81
    "
    0.79
     really
    0.78
     definitely
    0.76
    Activations Density 0.356%

    No Known Activations