© 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. 10-RES-JB
    11. 2797
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and words associated with criticism

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.20
    0.6%
    1526
    +0.07
    0.2%
    382
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.20
    0.09
    1013
    +0.07
    0.12
    1363
    +0.07
    0.08
    Negative Logits
    <bos>
    -2.14
    fputs
    -0.57
    lay
    -0.56
    also
    -0.55
    ///**
    -0.55
    ുറ
    -0.55
     participate
    -0.55
    make
    -0.54
    home
    -0.54
     contribute
    -0.54
    POSITIVE LOGITS
     swarovski
    1.33
     Joaqu
    1.20
    capulco
    1.20
     ecru
    1.20
     Juf
    1.19
     paradiso
    1.16
     sacerd
    1.15
     Simult
    1.15
     pylab
    1.14
     jorge
    1.13
    Activations Density 1.937%

    No Known Activations