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. 547
    Prev
    Next
    INDEX
    Explanations

    phrases related to skateboarding and hockey

    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
    1350
    +0.24
    1.2%
    795
    +0.16
    0.8%
    1092
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1350
    +0.24
    0.04
    795
    +0.16
    0.04
    690
    +0.13
    0.03
    Negative Logits
     kuku
    -0.69
     rescin
    -0.67
     laim
    -0.65
     posteriorly
    -0.64
     zara
    -0.63
     traktor
    -0.63
     interposed
    -0.63
     condense
    -0.61
     coerce
    -0.60
     equalled
    -0.59
    POSITIVE LOGITS
     skating
    1.05
     skate
    1.02
     Hockey
    0.95
     skates
    0.94
     hockey
    0.93
    Skate
    0.92
     Skate
    0.88
     Skating
    0.87
     rink
    0.86
    Hockey
    0.83
    Activations Density 0.434%

    No Known Activations