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. 919
    Prev
    Next
    INDEX
    Explanations

    references to specific types of automotive races and vehicles

    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
    1573
    +0.21
    1.1%
    1023
    +0.16
    0.9%
    889
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.21
    0.05
    478
    +0.16
    0.03
    1573
    +0.15
    0.04
    Negative Logits
     يتيمه
    -0.84
     esquecer
    -0.76
     Heff
    -0.74
     Adamson
    -0.73
     intitulée
    -0.66
     véhic
    -0.65
     étu
    -0.65
     chois
    -0.62
     Thacker
    -0.62
     citoy
    -0.61
    POSITIVE LOGITS
     sprint
    0.97
     Sprint
    0.96
    Sprint
    0.90
     spr
    0.87
     sprints
    0.81
     Lombar
    0.79
     Spr
    0.77
     zyn
    0.73
     Sitten
    0.72
    sprint
    0.68
    Activations Density 0.722%

    No Known Activations