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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 15135
    Prev
    Next
    INDEX
    Explanations

    information related to economics, finance, research, and technological advancements in various regions and countries

    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
    +0.27
    1.1%
    1385
    +0.08
    0.3%
    227
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.27
    0.05
    939
    +0.08
    0.06
    1253
    +0.08
    0.03
    Negative Logits
    <bos>
    -3.06
     arrange
    -0.63
     relieve
    -0.62
     enable
    -0.60
     gather
    -0.59
     add
    -0.59
     personalize
    -0.58
     mogli
    -0.57
     put
    -0.57
    WireFormatLite
    -0.57
    POSITIVE LOGITS
     ecru
    1.66
     napoli
    1.54
     murano
    1.53
     affor
    1.53
     madonna
    1.50
     eiffel
    1.48
     swarovski
    1.48
     matel
    1.47
     lamborghini
    1.46
     bordeaux
    1.45
    Activations Density 2.180%

    No Known Activations