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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 15171
    Prev
    Next
    INDEX
    Explanations

    weather conditions and seasonal patterns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    0.7%
    1499
    +0.16
    0.6%
    736
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.18
    0.09
    1460
    +0.16
    0.04
    342
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.72
    ⓧ
    -0.97
    <?
    -0.95
    PerformLayout
    -0.87
    /**
    -0.87
    Autoritní
    -0.80
    EndGlobalSection
    -0.75
    <?
    
    -0.73
    awtextra
    -0.72
    archiviato
    -0.70
    POSITIVE LOGITS
     thut
    1.58
     stockholm
    1.54
     maneu
    1.52
     effe
    1.52
     nece
    1.49
     accla
    1.48
     desir
    1.46
     ftu
    1.45
     parch
    1.44
     affor
    1.41
    Activations Density 0.632%

    No Known Activations