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. 124
    Prev
    Next
    INDEX
    Explanations

    references to dragons

    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
    +0.22
    1.2%
    732
    +0.14
    0.7%
    122
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    732
    +0.22
    0.02
    489
    +0.14
    0.01
    1622
    +0.12
    0.01
    Negative Logits
    <bos>
    -2.21
    لينكات
    -0.66
    homonymie
    -0.65
    })();
    
    -0.65
    CodedInputStream
    -0.64
    IsRequired
    -0.64
    LabelTagHelper
    -0.62
    },[])
    -0.62
     وتسجيلات
    -0.60
    CodeDom
    -0.60
    POSITIVE LOGITS
     impractica
    1.48
     Khart
    1.47
     unwarran
    1.46
     saar
    1.44
     increa
    1.44
     Intere
    1.43
     impra
    1.41
     Augu
    1.41
     Bartholo
    1.40
     Juf
    1.38
    Activations Density 0.069%

    No Known Activations