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

    Neuronpedia

    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. 0-RES-JB
    11. 687
    Prev
    Next
    INDEX
    Explanations

    words related to a specific sports organization

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    597
    +0.10
    0.3%
    680
    +0.09
    0.3%
    1047
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.10
    0.04
    174
    +0.09
    0.02
    1120
    +0.09
    0.03
    Negative Logits
     recovered
    -0.59
     nghi
    -0.58
     باد
    -0.56
     play
    -0.56
     recover
    -0.56
     extend
    -0.56
     hoped
    -0.56
    ปก
    -0.54
     stole
    -0.53
     register
    -0.53
    POSITIVE LOGITS
     UFC
    2.35
    UFC
    2.15
     ufc
    1.75
     MMA
    1.25
     effe
    1.22
     embodi
    1.16
     vété
    1.10
     Abbé
    1.09
     fup
    1.07
     mma
    1.07
    Activations Density 0.253%

    No Known Activations