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. 8342
    Prev
    Next
    INDEX
    Explanations

    data related to inventory and product management for specific items

    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
    +0.17
    0.5%
    1741
    +0.12
    0.4%
    1699
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.17
    -0.00
    185
    +0.12
    0.03
    1343
    +0.11
    0.04
    Negative Logits
     even
    -0.65
    将
    -0.62
     those
    -0.60
     going
    -0.59
     at
    -0.58
    的两
    -0.58
    会
    -0.58
     nearly
    -0.58
    进行
    -0.57
     behind
    -0.57
    POSITIVE LOGITS
     milano
    1.53
     meis
    1.51
     dora
    1.49
     franz
    1.49
     doman
    1.47
     canel
    1.43
     matel
    1.43
     nutr
    1.41
     kef
    1.41
     pira
    1.40
    Activations Density 0.239%

    No Known Activations