© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1535
    Prev
    Next
    INDEX
    Explanations

    people's names, especially the name "Kyle"

    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
    1492
    +0.24
    1.3%
    1222
    +0.16
    0.9%
    1961
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1492
    +0.24
    0.04
    1097
    +0.16
    0.04
    690
    +0.15
    0.03
    Negative Logits
    <bos>
    -0.93
     coar
    -0.60
    jątk
    -0.59
     witcher
    -0.55
     inconce
    -0.55
     cuck
    -0.55
     embo
    -0.55
     DbSet
    -0.54
    andaag
    -0.52
    
    -0.52
    POSITIVE LOGITS
     Kyle
    1.34
    Kyle
    1.32
    kyle
    0.89
     kram
    0.82
     maksi
    0.81
     lü
    0.81
     kog
    0.80
     vne
    0.79
     naer
    0.78
     pól
    0.77
    Activations Density 0.588%

    No Known Activations