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. 15128
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations and numerical values

    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
    1385
    +0.11
    0.3%
    1978
    +0.11
    0.3%
    876
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.11
    0.03
    382
    +0.11
    0.03
    985
    +0.11
    0.03
    Negative Logits
     shenan
    -1.34
     depic
    -1.21
     philanth
    -1.16
     pamph
    -1.16
     maneu
    -1.14
     intrigu
    -1.14
     sophistic
    -1.13
     enthusi
    -1.12
     caprice
    -1.10
     attemp
    -1.10
    POSITIVE LOGITS
     magasiner
    0.70
     CreateTagHelper
    0.69
     sumpay
    0.61
    paralleled
    0.60
    memoized
    0.59
    tonode
    0.57
     lapto
    0.57
    mistak
    0.57
    larged
    0.57
    WillAppear
    0.55
    Activations Density 0.146%

    No Known Activations