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. 8360
    Prev
    Next
    INDEX
    Explanations

    dates or years indicated in text data

    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
    1343
    +0.18
    0.6%
    630
    +0.11
    0.3%
    2019
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.18
    0.02
    450
    +0.11
    0.03
    630
    +0.11
    0.03
    Negative Logits
     hairc
    -1.18
     swarovski
    -0.95
     amigurumi
    -0.94
     shenan
    -0.93
     ecru
    -0.92
     impra
    -0.88
     pegasus
    -0.87
     satchel
    -0.87
     schoolmaster
    -0.86
     paisley
    -0.86
    POSITIVE LOGITS
     apparti
    0.63
    4
    0.62
    1
    0.61
     meras
    0.60
    8
    0.60
    7
    0.60
    2
    0.60
    6
    0.59
    3
    0.59
     Ottobre
    0.59
    Activations Density 0.028%

    No Known Activations