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. 3046
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing the pros and cons of a topic

    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
    203
    +0.09
    0.3%
    1675
    +0.09
    0.2%
    80
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1675
    +0.09
    0.05
    990
    +0.09
    0.03
    852
    +0.07
    0.03
    Negative Logits
     voleva
    -0.81
     faceva
    -0.77
     vogli
    -0.73
     dichi
    -0.69
     aspetta
    -0.68
     intende
    -0.67
     lavora
    -0.67
     sape
    -0.66
     sappi
    -0.65
     dimenti
    -0.64
    POSITIVE LOGITS
     benefits
    0.81
     advantages
    0.79
     Disadvantages
    0.77
    benefits
    0.77
     Benefits
    0.76
     disadvantages
    0.73
     Advantages
    0.73
    Benefits
    0.71
     downsides
    0.70
     drawbacks
    0.69
    Activations Density 0.284%

    No Known Activations