Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7774
    Prev
    Next
    INDEX
    Explanations

    references to characters and relationships in movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.39
    1.4%
    908
    +0.09
    0.3%
    906
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2009
    +0.39
    0.09
    908
    +0.09
    0.05
    547
    +0.07
    0.05
    Negative Logits
    <bos>
    -1.74
    InputBorder
    -0.65
     prek
    -0.58
    ValueGeneration
    -0.58
    DockStyle
    -0.56
     skr
    -0.56
     metr
    -0.56
     rada
    -0.56
    AndEndTag
    -0.55
     Wikimédia
    -0.54
    POSITIVE LOGITS
     accla
    1.27
     maneu
    1.16
     emphat
    1.15
     indescri
    1.09
     🤣🤣
    1.06
     unspeak
    1.05
     disgra
    1.04
     hairc
    1.02
     disreg
    1.02
     inconce
    1.01
    Activations Density 1.545%

    No Known Activations