© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 5035
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition and performance outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.9%
    1013
    +0.14
    0.6%
    2034
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.23
    0.13
    1013
    +0.14
    0.11
    509
    +0.13
    0.10
    Negative Logits
    <bos>
    -2.76
     intersper
    -1.64
     encomp
    -1.37
     fuf
    -1.29
     ?...
    -1.26
     !...
    -1.20
     emphat
    -1.19
     fta
    -1.16
     ftu
    -1.15
     fte
    -1.12
    POSITIVE LOGITS
     during
    0.69
     wüns
    0.67
    ]=="
    0.66
     kapag
    0.66
    URLEncoder
    0.66
    hastly
    0.65
     throughout
    0.64
    cautionary
    0.64
     adecuados
    0.64
    astrous
    0.63
    Activations Density 0.891%

    No Known Activations