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. 3014
    Prev
    Next
    INDEX
    Explanations

    emotional and impactful moments or situations in stories and experiences

    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
    1013
    +0.13
    0.4%
    1899
    +0.09
    0.2%
    964
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.13
    0.06
    1490
    +0.09
    0.06
    1969
    +0.08
    0.05
    Negative Logits
     tenda
    -0.69
     polig
    -0.64
     palio
    -0.63
     sonda
    -0.63
     raya
    -0.62
     masaj
    -0.61
     Lucía
    -0.58
     sucul
    -0.57
     farmacia
    -0.57
     beneficia
    -0.57
    POSITIVE LOGITS
     coö
    0.63
    whenever
    0.61
     nutella
    0.60
     Abbé
    0.55
     realizing
    0.55
     Reiche
    0.54
     Gorb
    0.54
     Rine
    0.54
     Scherer
    0.54
     subgoals
    0.53
    Activations Density 0.375%

    No Known Activations