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. 340
    Prev
    Next
    INDEX
    Explanations

    positive sentiments and expressions of hope or support

    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
    1373
    +0.08
    0.2%
    1677
    +0.08
    0.2%
    555
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1677
    +0.08
    0.06
    839
    +0.08
    0.03
    1276
    +0.08
    0.05
    Negative Logits
     sappi
    -0.98
     centrif
    -0.96
     guatemala
    -0.92
     hcm
    -0.90
     alberto
    -0.89
     uruguay
    -0.88
     labd
    -0.87
     lele
    -0.87
     canel
    -0.87
     jorge
    -0.87
    POSITIVE LOGITS
     nevertheless
    0.94
     nonetheless
    0.89
     fortunately
    0.82
     luckily
    0.78
     thankfully
    0.73
     hey
    0.67
     persever
    0.67
     persevere
    0.61
     reassured
    0.60
     зато
    0.60
    Activations Density 0.368%

    No Known Activations