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. 15808
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts

    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
    604
    +0.12
    0.4%
    939
    +0.10
    0.3%
    1553
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.12
    0.07
    1553
    +0.10
    0.07
    488
    +0.09
    0.06
    Negative Logits
     shenan
    -1.41
     intersper
    -1.39
     snoopy
    -1.28
     disgra
    -1.27
     accla
    -1.26
     maneu
    -1.26
     milf
    -1.26
     hentai
    -1.24
     peppa
    -1.23
     unspeak
    -1.21
    POSITIVE LOGITS
     restrictions
    1.08
     restriction
    1.06
     restrict
    0.97
     restrictive
    0.95
    restriction
    0.90
     restricted
    0.89
     restricting
    0.86
    restrict
    0.84
     prohibition
    0.79
     restric
    0.78
    Activations Density 0.851%

    No Known Activations