© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2096
    Prev
    Next
    INDEX
    Explanations

    phrases related to sporting events, specifically the World Cup

    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
    1552
    +0.07
    0.2%
    131
    +0.07
    0.2%
    1173
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.07
    0.04
    1552
    +0.07
    0.03
    710
    +0.06
    0.03
    Negative Logits
    <bos>
    -0.97
    ⓧ
    -0.80
     earn
    -0.68
     become
    -0.68
     extend
    -0.67
      
    -0.67
     manage
    -0.67
     destroy
    -0.66
    .
    -0.66
        
    -0.66
    POSITIVE LOGITS
     fta
    2.09
     aen
    2.06
     ftu
    1.99
     effe
    1.99
     thut
    1.98
     fup
    1.95
     fte
    1.86
     nece
    1.84
     vns
    1.81
     wien
    1.80
    Activations Density 0.201%

    No Known Activations