Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1877
    Prev
    Next
    INDEX
    Explanations

    feelings of inadequacy and the desire for affirmation

    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
    1842
    +0.26
    1.0%
    50
    +0.23
    0.9%
    1967
    +0.21
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1166
    +0.26
    0.10
    1967
    +0.23
    0.10
    1978
    +0.21
    0.10
    Negative Logits
    <bos>
    -1.63
    /***
    
    -0.61
     initComponents
    -0.59
    Manbalar
    -0.53
     unify
    -0.52
     kasarigan
    -0.51
    citenamefont
    -0.51
     intersper
    -0.50
    Erreferentziak
    -0.50
     also
    -0.50
    POSITIVE LOGITS
     swarovski
    1.20
     ecru
    1.18
     broderie
    1.00
     paradiso
    0.97
     NDEBUG
    0.91
     riva
    0.90
     Décembre
    0.90
     tricot
    0.90
     murano
    0.88
     paillettes
    0.88
    Activations Density 1.735%

    No Known Activations