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. 1497
    Prev
    Next
    INDEX
    Explanations

    words related to awards and achievements in the context of sports

    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
    599
    +0.10
    0.3%
    764
    +0.08
    0.2%
    1499
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.10
    0.03
    718
    +0.08
    0.02
    761
    +0.08
    0.02
    Negative Logits
     tetrach
    -0.89
     effe
    -0.88
     shewn
    -0.86
     liberality
    -0.84
     anhyd
    -0.83
     pollut
    -0.80
     nutella
    -0.80
     onely
    -0.80
     unlaw
    -0.79
     fta
    -0.79
    POSITIVE LOGITS
     konkre
    0.88
     kosme
    0.79
     konserv
    0.73
     kompati
    0.72
     distrik
    0.72
     infrastruktur
    0.71
     minimalis
    0.69
     praktik
    0.69
     kriminal
    0.69
     vertik
    0.68
    Activations Density 0.118%

    No Known Activations