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. 15787
    Prev
    Next
    INDEX
    Explanations

    details related to intelligence tests and cognitive assessments

    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
    876
    +0.21
    0.6%
    1499
    +0.15
    0.5%
    283
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.21
    0.06
    876
    +0.15
    -0.01
    283
    +0.12
    -0.00
    Negative Logits
     laity
    -0.51
     iniquity
    -0.50
     årets
    -0.47
     tragedy
    -0.46
     Juventud
    -0.46
    irée
    -0.46
    nemies
    -0.45
     Halen
    -0.45
     Başkanı
    -0.45
    远
    -0.45
    POSITIVE LOGITS
     overla
    1.32
     stik
    1.32
     makro
    1.31
     pessi
    1.29
     maneu
    1.23
     abnorm
    1.23
     umo
    1.23
     kug
    1.18
     kark
    1.17
     emphat
    1.17
    Activations Density 0.281%

    No Known Activations